Kyushu University Academic Staff Educational and Research Activities Database
List of Papers
Seiichi Uchida Last modified date:2019.08.04

Professor / Real World Robotics / Department of Advanced Information Technology / Faculty of Information Science and Electrical Engineering


Papers
1. Xiaomeng Wu, Akisato Kimura, Seiichi Uchida, and Kunio Kashino, Prewarping Siamese Network: Learning Local Representations For Online Signature Verification, Proceedings of the 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019, Brighton, UK), 2019.05.
2. Brian Kenji Iwana and Seiichi Uchida, Dynamic Weight Alignment for Temporal Convolutional Neural Networks, Proceedings of the 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019, Brighton, UK), 2019.05.
3. Hideaki Hayashi and Seiichi Uchida , A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction, Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018, Perth, Australia), 2018.12.
4. Frédéric Rayar, Seiichi Uchida, On Fast Sample Preselection for Speeding up Convolutional Neural Network Training, Proceedings of IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition (S+SSPR2018, Beijing, China), 2018.08.
5. Frédéric Rayar, Seiichi Uchida, An Image-Based Representation for Graph Classification, Proceedings of IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition (S+SSPR2018, Beijing, China), 2018.08.
6. Yuchen Zheng, Brian Kenji Iwana, Seiichi Uchida, Mining the displacement of max-pooling for text recognition, Pattern Recognition, 10.1016/j.patcog.2019.05.014, 93, 558-569, 2019.09, The max-pooling operation in convolutional neural networks (CNNs)downsamples the feature maps of convolutional layers. However, in doing so, it loses some spatial information. In this paper, we extract a novel feature from pooling layers, called displacement features, and combine them with the features resulting from max-pooling to capture the structural deformations for text recognition tasks. The displacement features record the location of the maximal value in a max-pooling operation. Furthermore, we analyze and mine the class-wise trends of the displacement features. The extensive experimental results and discussions demonstrate that the proposed displacement features can improve the performance of the CNN based architectures and tackle the issues with the structural deformations of max-pooling in the text recognition tasks..
7. Frédéric Rayar, Seiichi Uchida, Comic text detection using neural network approach, 25th International Conference on MultiMedia Modeling, MMM 2019 MultiMedia Modeling - 25th International Conference, MMM 2019, Proceedings, 10.1007/978-3-030-05716-9_60, 672-683, 2019.01, Text is a crucial element in comic books; hence text detection is a significant challenge in an endeavour to achieve comic processing. In this work, we study in what extent an off-the-shelf neural network approach for scene text detection can be used to perform comic text detection. Experiment on a public data set shows that such an approach allows to perform as well as methods of the literature, which is promising for building more accurate comic text detector in the future..
8. Daisuke Matsuoka, Masuo Nakano, Daisuke Sugiyama, Seiichi Uchida, Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model, Progress in Earth and Planetary Science, 10.1186/s40645-018-0245-y, 5, 1, 2018.12, We propose a deep learning approach for identifying tropical cyclones (TCs) and their precursors. Twenty year simulated outgoing longwave radiation (OLR) calculated using a cloud-resolving global atmospheric simulation is used for training two-dimensional deep convolutional neural networks (CNNs). The CNNs are trained with 50,000 TCs and their precursors and 500,000 non-TC data for binary classification. Ensemble CNN classifiers are applied to 10 year independent global OLR data for detecting precursors and TCs. The performance of the CNNs is investigated for various basins, seasons, and lead times. The CNN model successfully detects TCs and their precursors in the western North Pacific in the period from July to November with a probability of detection (POD) of 79.9–89.1% and a false alarm ratio (FAR) of 32.8–53.4%. Detection results include 91.2%, 77.8%, and 74.8% of precursors 2, 5, and 7 days before their formation, respectively, in the western North Pacific. Furthermore, although the detection performance is correlated with the amount of training data and TC lifetimes, it is possible to achieve high detectability with a POD exceeding 70% and a FAR below 50% during TC season for several ocean basins, such as the North Atlantic, with a limited sample size and short lifetime. [Figure not available: see fulltext.]..
9. Kotaro Abe, Brian Kenji Iwana, Viktor Gösta Holmér and Seiichi Uchida, Font Creation Using Generative Adversarial Networks with Class Discrimination, Proceedings of Asian Conference on Pattern Recognition (ACPR2017, Nanjing, China), 2017.10.
10. Shailza Jolly, Brian Kenji Iwana, Ryohei Kuroki, Seiichi Uchida, How do Convolutional Neural Networks Learn Design?, Proceedings of the 24th International Conference on Pattern Recognition (ICPR2018, Beijing, China), 2018.08.
11. Brian Kenji Iwana, Minoru Mori, Akisato Kimura and Seiichi Uchida, Introducing Local Distance-based Features to Temporal Convolutional Neural Networks , Proceedings of 16th International Conference on Frontiers in Handwriting Recognition (ICFHR2018, Niagara Falls, USA) , 2018.08.
12. Yuchen Zheng, Brian Kenji Iwana and Seiichi Uchida, Discovering Class-wise Trends of Max-pooling in Subspace, Proceedings of 16th International Conference on Frontiers in Handwriting Recognition (ICFHR2018, Niagara Falls, USA), 2018.08.
13. Maoko Tsukamoto, Kyoko Chiba, Yuriko Sobu, Yuzuha Shiraki, Yuka Okumura, Saori Hata, Akira Kitamura, Tadashi Nakaya, Seiichi Uchida, Masataka Kinjo, Hidenori Taru, Toshiharu Suzuki, The cytoplasmic region of the amyloid β-protein precursor (APP) is necessary and sufficient for the enhanced fast velocity of APP transport by kinesin-1, FEBS Letters, 10.1002/1873-3468.13204, 592, 16, 2716-2724, 2018.08, Amyloid β-protein precursor (APP) is transported mainly by kinesin-1 and at a higher velocity than other kinesin-1 cargos, such as Alcadein α (Alcα); this is denoted by the enhanced fast velocity (EFV). Interaction of the APP cytoplasmic region with kinesin-1, which is essential for EFV transport, is mediated by JNK-interacting protein 1 (JIP1). To determine the roles of interactions between the APP luminal region and cargo components, we monitored transport of chimeric cargo receptors, Alcα (luminal)–APP (cytoplasmic) and APP (luminal)–Alcα (cytoplasmic). Alcα-APP is transported at the EFV, whereas APP-Alcα is transported at the same velocity as wild-type Alcα. Thus, the cytoplasmic region of APP is necessary and sufficient for the EFV of APP transport by kinesin-1..
14. Anna Zhu, Seiichi Uchida, Scene word recognition from pieces to whole, Frontiers of Computer Science, 10.1007/s11704-017-6420-2, 1-10, 2018.04, Convolutional neural networks (CNNs) have had great success with regard to the object classification problem. For character classification, we found that training and testing using accurately segmented character regions with CNNs resulted in higher accuracy than when roughly segmented regions were used. Therefore, we expect to extract complete character regions from scene images. Text in natural scene images has an obvious contrast with its attachments. Many methods attempt to extract characters through different segmentation techniques. However, for blurred, occluded, and complex background cases, those methods may result in adjoined or over segmented characters. In this paper, we propose a scene word recognition model that integrates words from small pieces to entire after-cluster-based segmentation. The segmented connected components are classified as four types: background, individual character proposals, adjoined characters, and stroke proposals. Individual character proposals are directly inputted to a CNN that is trained using accurately segmented character images. The sliding window strategy is applied to adjoined character regions. Stroke proposals are considered as fragments of entire characters whose locations are estimated by a stroke spatial distribution system. Then, the estimated characters from adjoined characters and stroke proposals are classified by a CNN that is trained on roughly segmented character images. Finally, a lexicondriven integration method is performed to obtain the final word recognition results. Compared to other word recognition methods, our method achieves a comparable performance on Street View Text and the ICDAR 2003 and ICDAR Received August 22, 2016; accepted March 12, 2017 E-mail: annakkk@live.com 2013 benchmark databases. Moreover, our method can deal with recognizing text images of occlusion and improperly segmented text images..
15. Frédéric Rayar, Masanori Goto and Seiichi Uchida, CNN Training with Graph-Based Sample Preselection: Application to Handwritten Character Recognition, Proceedings of The 13th IAPR International Workshop on Document Analysis Systems (DAS2018, Viena, Austria), 2018.04.
16. Liuan Wang, Jun Sun and Seiichi Uchida, Text Line Extraction based on Integrated K-shortest Paths Optimization, Proceedings of The 13th IAPR International Workshop on Document Analysis Systems (DAS2018, Viena, Austria), 2018.04.
17. Gantugs Atarsaikhan, Brian Kenji Iwana and Seiichi Uchida, Contained Neural Style Transfer for Decorated Logo Generation, Proceedings of The 13th IAPR International Workshop on Document Analysis Systems (DAS2018, Viena, Austria), 2018.04.
18. Liuan Wang, Seiichi Uchida, Anna Zhu, Jun Sun, Human Reading Knowledge Inspired Text Line Extraction, Cognitive Computation, 10.1007/s12559-017-9490-4, 10, 1, 84-93, 2018.02, Text in images contains exact semantic information and the text knowledge can be utilized in many image cognition and understanding applications. The human reading habits can provide the clues of text line structure for text line extraction. In this paper, we propose a novel human reading knowledge inspired text line extraction method based on k-shortest paths global optimization. Firstly, the candidate character extraction is reformulated as Maximal Stable Extremal Region (MSER) algorithm on gray, red, blue, and green channels of the target images, and the extracted MSERs are fed into Convolutional Neural Network (CNN) to remove the noise components. Then, the directed graph is built upon the character component nodes with edges inspired by human reading sense. The directed graph can automatically construct the relationship to eliminate the disorder of candidate text components. The text line paths optimization is inspired by the human reading ability in planning of a text line path sequentially. Therefore, the text line extraction problem can be solved using the k-shortest paths optimization algorithm by taking advantage of the human reading sense structure of the directed graph. It can extract the text lines iteratively to avoid the exhaustive searching and obtain global optimized text line number. The proposed method achieves the f-measure of 0.820 and 0.812 on public ICDAR2011 and ICDAR2013 dataset, respectively. The experimental results demonstrate the effectiveness of the proposed human reading knowledge inspired text line extraction method in comparison with state-of-the-art methods This paper presents one human reading knowledge inspired text line extraction method, which approves that the human reading knowledge can benefit the text line extraction and image text discovery..
19. Brian Kenji Iwana, Letao Zhou, Kumiko Tanaka-Ishii, Seiichi Uchida, Component Awareness in Convolutional Neural Networks, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, 10.1109/ICDAR.2017.72, 1, 394-399, 2018.01, In this work, we investigate the ability of Convolutional Neural Networks (CNN) to infer the presence of components that comprise an image. In recent years, CNNs have achieved powerful results in classification, detection, and segmentation. However, these models learn from instance-level supervision of the detected object. In this paper, we determine if CNNs can detect objects using image-level weakly supervised labels without localization. To demonstrate that a CNN can infer awareness of objects, we evaluate a CNN's classification ability with a database constructed of Chinese characters with only character-level labeled components. We show that the CNN is able to achieve a high accuracy in identifying the presence of these components without specific knowledge of the component. Furthermore, we verify that the CNN is deducing the knowledge of the target component by comparing the results to an experiment with the component removed. This research is important for applications with large amounts of data without robust annotation such as Chinese character recognition..
20. Jinho Lee, Brian Kenji Iwana, Shouta Ide, Hideaki Hayashi, Seiichi Uchida, Globally Optimal Object Tracking with Complementary Use of Single Shot Multibox Detector and Fully Convolutional Network, 8th Pacific-Rim Symposium on Image and Video Technology, PSIVT 2017 Image and Video Technology - 8th Pacific-Rim Symposium, PSIVT 2017, Revised Selected Papers, 10.1007/978-3-319-75786-5_10, 110-122, 2018.01, Object tracking is one of the most important but still difficult tasks in computer vision and pattern recognition. The main difficulties in the tracking task are appearance variation of target objects and occlusion. To deal with those difficulties, we propose a object tracking method combining Single Shot Multibox Detector (SSD), Fully Convolutional Network (FCN) and Dynamic Programming (DP). SSD and FCN provide a probability value of the target object which allows for appearance variation within each category. DP provides a globally optimal tracking path even with severe occlusions. Through several experiments, we confirmed that their combination realized a robust object tracking method. Also, in contrast to traditional trackers, initial position and a template of the target do not need to be specified. We show that the proposed method has a higher performance than the traditional trackers in tracking various single objects through video frames..
21. Shota Ide, Seiichi Uchida, How Does a CNN Manage Different Printing Types?, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, 10.1109/ICDAR.2017.167, 1, 1004-1009, 2018.01, In past OCR research, different OCR engines are used for different printing types, i.e., machine-printed characters, handwritten characters, and decorated fonts. A recent research, however, reveals that convolutional neural networks (CNN) can realize a universal OCR, which can deal with any printing types without pre-classification into individual types. In this paper, we analyze how CNN for universal OCR manage the different printing types. More specifically, we try to find where a handwritten character of a class and a machine-printed character of the same class are 'fused' in CNN. For analysis, we use two different approaches. The first approach is statistical analysis for detecting the CNN units which are sensitive (or insensitive) to type difference. The second approach is network-based visualization of pattern distribution in each layer. Both analyses suggest the same trend that types are not fully fused in convolutional layers but the distributions of the same class from different types become closer in upper layers..
22. Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai, Seiichi Uchida, Neural Font Style Transfer, 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017 Proceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017, 10.1109/ICDAR.2017.328, 5, 51-56, 2018.01, In this paper, we chose an approach to generate fonts by using neural style transfer. Neural style transfer uses Convolution Neural Networks(CNN) to transfer the style of one image to another. By modifying neural style transfer, we can achieve neural font style transfer. We also demonstrate the effects of using different weighted factors, character placements, and orientations. In addition, we show the results of using non-Latin alphabets, non-text patterns, and non-text images as style images. Finally, we provide insight into the characteristics of style transfer with fonts..
23. Toshiki Nakamura, Anna Zhu, Keiji Yanai, Seiichi Uchida, Scene Text Eraser, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, 10.1109/ICDAR.2017.141, 1, 832-837, 2018.01, The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished byaCNNmodelthroughconvolutiontodeconvolutionwithinterconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images..
24. Anna Zhu, Seiichi Uchida, Scene Text Relocation with Guidance, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, 10.1109/ICDAR.2017.212, 1, 1289-1294, 2018.01, Applying object proposal technique for scene text detection becomes popular for its significant improvement in speed and accuracy for object detection. However, some of the text regions after the proposal classification are overlapped and hard to remove or merge. In this paper, we present a scene text relocation system that refines the detection from text proposals to text. An object proposal-based deep neural network is employed to get the text proposals. To tackle the detection overlapping problem, a refinement deep neural network relocates the overlapped regions by estimating the text probability inside, and locating the accurate text regions by thresholding. Since the spacebetweenwordsindifferenttextlinesarevarious, aguidance mechanism is proposed in text relocation to guide where to extract the text regions in word level. This refinement procedure helps boost the precision after removing multiple overlapped text regions or joint cracked text regions. The experimental results on standard benchmark ICDAR 2013 demonstrate the effectiveness of the proposed approach..
25. Koichi Kise, Shinichiro Omachi, Seiichi Uchida, Masakazu Iwamura, Welcome Message from the ICDAR 2017 General and Executive Chairs, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 10.1109/ICDAR.2017.5, 1, xxiv-xxv, 2018.01.
26. Tomohiro Nakayasu, Masaki Yasugi, Soma Shiraishi, Seiichi Uchida, Eiji Watanabe, Three-Dimensional Computer Graphic Animations for Studying Social Approach Behaviour in Medaka Fish: Effects of Systematic Manipulation of Morphological and Motion Cues , PLoS ONE, 2017.04.
27. Brian K. Iwana, Kaspar Riesen, Volkmar Frinken, Seiichi Uchida, Efficient Temporal Pattern Recognition by Means of Dissimilarity Space Embedding with Discriminative Prototypes , Pattern Recognition, 2017.04.
28. Koichi Kise, Shinichiro Omachi, Seiichi Uchida, Masakazu Iwamura, Masahiko Inami, Kai Kunze, Reading-life log as a new paradigm of utilizing character and document media, Horizontal Expansion, 10.1007/978-4-431-56535-2_7, 2, 197-233, 2017.04, "You are what you read." As this sentence implies, reading is important for building our minds. We are investing a huge amount of time for reading to input information. However the activity of "reading" is done only by each individual in an analog way and nothing is digitally recorded and reused. In order to solve this problem, we record reading activities as digital data and analyze them for various goals. We call this research "reading-life log." In this chapter, we describe our achievements of the reading-life log. A target of the reading-life log is to analyze reading activities quantitatively and qualitatively: when, how much, what you read, and how you read in terms of your interests and understanding. Body-worn sensors including intelligent eyewear are employed for this purpose. Another target is to analyze the contents of documents based on the users' reading activities: for example, which are the parts most people feel difficult/interesting. Materials to be read are not limited to books and documents. Scene texts are also important materials which guide human activities..
29. Kenji Kimura, Alexandre Mamane, Tohru Sasaki, Kohta Sato, Jun Takagi, Ritsuya Niwayama, Lars Hufnagel, Yuta Shimamoto, Jean-François Joanny, Seiichi Uchida, Akatsuki Kimura, Endoplasmic-Reticulum-Mediated Microtubule Alignment Governs Cytoplasmic Streaming , Nature Cell Biology, 2017.03.
30. Yuki Sato, Kei Nagatoshi, Ayumi Hamano, Yuko Imamura, David Huss, Seiichi Uchida, Rusty Lansford, Basal Filopodia and Vascular Mechanical Stress Organize Fibronectin into Pillars Bridging the Mesoderm-Endoderm Gap , Development, 2017.02.
31. Masanori Goto, Ryosuke Ishida, Seiichi Uchida, A Preselection-Based Fast Support Vector Machine Learning for Large-Scale Pattern Sets using Compressed Relative Neighborhood Graph, Research Reports on Information Science and Electrical Engineering of Kyushu University, 22, 1, 1-7, 2017.01, We propose a pre-selection method for training support vector machines (SVM) with a largescale dataset. Specifically, the proposed method selects patterns around the class boundary and the selected data is fed to train an SVM. For the selection, that is, searching for boundary patterns, we utilize a compressed representation of relative neighborhood graph (Clustered-RNG). A Clustered-RNG is a network of neighboring patterns which have a different class label and thus, we can find boundary patterns between different classes. Through large-scale handwritten digit pattern recognition experiments, we show that the proposed pre-selection method accelerates SVM training process 10 times faster without degrading recognition accuracy..
32. Seiichi Uchida, Shota Ide, Brian Kenji Iwana, Anna Zhu, A further step to perfect accuracy by training CNN with larger data, 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016, 10.1109/ICFHR.2016.0082, 405-410, 2017.01, Convolutional Neural Networks (CNN) are on the forefront of accurate character recognition. This paper explores CNNs at their maximum capacity by implementing the use of large datasets. We show a near-perfect performance by using a dataset of about 820,000 real samples of isolated handwritten digits, much larger than the conventional MNIST database. In addition, we report a near-perfect performance on the recognition of machine-printed digits and multi-font digital born digits. Also, in order to progress toward a universal OCR, we propose methods of combining the datasets into one classifier. This paper reveals the effects of combining the datasets prior to training and the effects of transfer learning during training. The results of the proposed methods also show an almost perfect accuracy suggesting the ability of the network to generalize all forms of text..
33. Brian Kenji Iwana, Volkmar Frinken, Seiichi Uchida, A robust dissimilarity-based neural network for temporal pattern recognition, 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016 Proceedings - 2016 15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016, 10.1109/ICFHR.2016.0058, 265-270, 2017.01, Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods..
34. Seiichi Uchida and Yuto Shinahara, What Does Scene Text Tell Us?, Proceedings of the 23rd International Conference on Pattern Recognition, 2016.12.
35. Brian Iwana, Seiichi Uchida and Volkmar Frinken, A Robust Dissimilarity-based Neural Network for Temporal Pattern Recognition, Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition, 2016.10.
36. Seiichi Uchida, Shota Ide, Brian Iwana and Anna Zhu, A Further Step to Perfect Accuracy by Training CNN with Larger Data, Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition, 2016.10.
37. Zhu Anna, Renwu Gao, Seiichi Uchida, Could Scene Context be Beneficial for Scene Text Detection?, Pattern Recognition, 10.1016/j.patcog.2016.04.011, 2016.10.
38. Shigeru Matsumura, Tomoko Kojidani, Yuji Kamioka, Seiichi Uchida, Tokuko Haraguchi, Akatsuki Kimura, Fumiko Toyoshima, Interphase adhesion geometry is transmitted to an internal regulator for spindle orientation via caveolin-1, Nature Communications, 2016.06.
39. Markus Goldstein, Seiichi Uchida, A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data, PLoS ONE, 10.1371/journal.pone.0152173, 11, 4, e0152173, 2016.04.
40. Liuan Wang, Seiichi Uchida, Wei Fan, Jun Sun, Globally Optimal Text Line Extraction based on K-Shortest Paths algorithm, Proceedings of The 12th IAPR International Workshop on Document Analysis Systems (DAS2016), 2016.03.
41. Kana Aoki, Fumiyo Maeda, Tomoya Nagasako, Seiichi Uchida, Junichi Ikenouchi, A RhoA and Rnd3 cycle regulates actin reassembly during membrane blebbing, Proceedings of the National Academy of Sciences (PNAS), 2016.03.
42. Markus Goldstein, Seiichi Uchida, A Comparative Study on Outlier Removal from a Large-scale Dataset using Unsupervised Anomaly Detection, Proceedings of The 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM2016), 2016.02.
43. Jiamin Xu, Palaiahnakote Shivakumara, Tong Lu, Chew Lim Tan, 内田誠一, A New Method for Multi Oriented Graphics-Scene-3D Text Classification in Video, Pattern Recognition, 10.1016/j.patcog.2015.07.002, 49, 1, 19-42, 2016.01.
44. Seiichi Uchida, Yuji Egashira, Kota Sato, Exploring the World of Fonts for Discovering the Most Standard Fonts and the Missing Fonts, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
45. Ryosuke Kakisako, Seiichi Uchida, Volkmar Frinken, Learning Non-Markovian Constraints for Handwriting Recognition, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
46. Volkmar Frinken, Seiichi Uchida, Deep BLSTM Neural Networks for Unconstrained Continuous Handwritten Text Recognition, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
47. Masanori Goto, Ryosuke Ishida, Seiichi Uchida, Preselection of Support Vector Candidates by Relative Neighborhood Graph for Large-Scale Character Recognition, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
48. Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghosh, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, Faisal Shafait, Seiichi Uchida, Ernest Valveny, ICDAR 2015 Competition on Robust Reading, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
49. Renwu Gao, Shoma Eguchi, Seiichi Uchida, True Color Distributions of Scene Text and Background, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
50. Brian Iwana, Seiichi Uchida, Kaspar Riesen, Volkmar Frinken, Tackling Pattern Recognition by Vector Space Embedding, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
51. Donato Barbuzzi, Giuseppe Pirlo, Seiichi Uchida, Volkmar Frinken, Donato Impedovo, Similarity-based Regularization for Semi-Supervised Learning for Handwritten Digit Recognition, Proceedings of The 13th International Conference on Document Analysis and Recognition (ICDAR 2015, Nancy, France), 2015.08.
52. Andreas Fischer, Seiichi Uchida, Volkmar Frinken, Kaspar Riesen, Horst Bunke, Improving Hausdorff Edit Distance Using Structural Node Context, Proceedings of the The 10th IAPR-TC15 Workshop on Graph-based Representations in Pattern Recognition, 2015.05.
53. Koichi Kise, Shinichiro Omachi, Seiichi Uchida, Masakazu Iwamura, Marcus Liwicki, Data Embedding into Characters, IEICE Transactions on Information & Systems, E98-D, 1.0, 2015.01.
54. Renwu Gao, Seiichi Uchida, Asif Shahab, Faisal Shafait, Volkmar Frinken, Visual Saliency Models for Text Detection in Real World, PLoS ONE, 9.0, 12.0, 2014.12.
55. Kyoko Chiba, Masahiko Araseki, Keisuke Nozawa, Keiko Furukori, Yoichi Araki, Takahide Matsushima, Tadashi Nakaya,Saori Hata, Yuhki Saito, Seiichi Uchida, Yasushi Okada, Angus C. Nairn, Roger J. Davis, Tohru Yamamoto, Masataka Kinjo, Hidenori Taru, and Toshiharu Suzuki, Quantitative Analysis of APP Axonal Transport in Neurons -- Role of JIP1 in Enhanced APP Anterograde Transport --, Molecular Biology of the Cell, 25.0, 22.0, 2014.11.
56. Cai Wenjie, Seiichi Uchida, Hiroaki Sakoe, Methods for Stroke-Order Free Online Multi-Stroke Character Recognition, Frontiers of Computer Science, 8.0, 5.0, 2014.10.
57. Rong Huang, Kyung hyune Rhee and Seichi Uchida, A Parallel Image Encryption Method Based on Compressive Sensing, Multimedia Tools and Applications, 72.0, 1.0, 2014.09.
58. Ryota Ogata, Minoru Mori, Volkmar Frinken and Seiichi Uchida, Constrained AdaBoost for Totally-Ordered Global Features, Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition, 2014.09.
59. Volkmar Frinken, Ryosuke Kakisako and Seiichi Uchida, A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and its Application to Handwritten Word Recognition, Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition, 2014.09.
60. Muhammad Imran Malik, Marcus Liwicki, Andreas Dengel, Seiichi Uchida and Volkmar Frinken, Automatic Signatures Stability Analysis And Verification Using Local Features, Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition, 2014.09.
61. Volkmar Frinken, Yutaro Iwakiri, Ryosuke Ishida, Kensho Fujisaki, Seiichi Uchida, Improving Point of View Scene Recognition by Considering Textual Data, Proceedings of the 22nd International Conference on Pattern Recognition, 2014.08.
62. Kohei Inai, Marten Palsson, Volkmar Frinken, Yaokai Feng, Seiichi Uchida, Selective Concealment of Characters for Privacy Protection, Proceedings of the 22nd International Conference on Pattern Recognition, 2014.08.
63. Markus Weber, Christopher Scholzel, Marcus Liwicki, Seiichi Uchida, Didier Stricker, LSTM-Based Early Recognition of Motion Patterns, Proceedings of the 22nd International Conference on Pattern Recognition, 2014.08.
64. Volkmar Frinken, Nilanjana Bhattacharya, Seiichi Uchida and Umapada Pal, Improved BLSTM Neural Networks for Recognition of On-line Bangla Complex Words, Proceedings of Joint International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition, 2014.08.
65. Kyoko Chiba, Yuki Shimada, Masataka Kinjo, Toshiharu Suzuki, Seiichi Uchida, Simple and Direct Assembly of Kymographs from Movies Using Kymomaker, Traffic, 15.0, 1.0, 1.0-11.0, 2014.01.
66. Megumi Chikano, Koichi Kise, Masakazu Iwamura, Seiichi Uchida, Shinichiro Omachi, Recovery and Localization of Handwritings by a Camera-Pen Based on
Tracking and Document Image Retrieval, Pattern Recognition Letters, 35.0, 1.0, 214.0-224.0, 2014.01.
67. Minoru Mori, Seiichi Uchida, Hitoshi Sakano, Global Feature for Online Character Recognition, Pattern Recognition Letters, 35.0, 1.0, 142.0-148.0, 2014.01.
68. Marcus Liwicki, Seiichi Uchida, Akira Yoshida, Masakazu Iwamura, Shinichiro Omachi, Koichi Kise, More than Ink - Realization of a Data-Embedding Pen, Pattern Recognition Letters, 35.0, 1.0, 246.0-255.0, 2014.01.
69. Kensho Fujisaki, Ayumi Hamano, Kenta Aoki, Yaokai Feng, Seiichi Uchida, Masahiko Araseki, Yuki Saito and Toshiharu Suzuki, Detection and Tracking Protein Molecules in Fluorescence Microscopic Video, Proceedings of The 1st International Workshop on BioImage Recognition (BIR'13, Ehime, Japan), 2013.12.
70. Ayumi Hamano, Kensho Fujisaki, Seiichi Uchida and Osamu Shiku, Stable Marriage Algorithm for Tracking Intracellular Objects, Proceedings of The 1st International Workshop on BioImage Recognition (BIR'13, Ehime, Japan), 2013.12.
71. Hiroaki Takebe, Seiichi Uchida, Efficient anchor graph hashing with data-dependent anchor selection, IEICE Transactions on Information & Systems, E96-D, 10.0, 2235.0-2244.0, 2013.10.
72. Rong Huang, Palaiahnakote Shivakumara, Yaokai Feng, Seiichi Uchida, Scene Character Detection and Recognition with Cooperative
Multiple-Hypothesis Framework, IEICE Transactions on Information & Systems, E96-D, 10.0, 2235.0-2244.0, 2013.10.
73. Koichi Ogawara, Masahiro Fukutomi, Seiichi Uchida, Yaokai Feng, A Voting-Based Sequential Pattern Recognition Method, PLoS ONE, 8.0, 10.0, e76980, 2013.10.
74. Koichi Kise, Riki Kudo, Masakazu Iwamura, Seiichi Uchida and Shinichiro Omachi, A Proposal of Writing-Life Log and Its Implementation Using a
Retrieval-Based Camera-Pen, Proceedings of the 16th International Graphonomics Society Conference (IGS 2013, Nara, Japan), 86.0-89.0, 2013.08.
75. Wenjie Cai, Seiichi Uchida and Hiroaki Sakoe, An Efficient Radical-Based Algorithm for Stroke-Order Free and
Stroke-Number Free Online Kanji Character Recognition, Proceedings of the 16th International Graphonomics Society Conference (IGS 2013, Nara, Japan), 82.0-85.0, 2013.08.
76. Takafumi Matsuo, Song Wang, Yaokai Feng and Seiichi Uchida, Exploring the Ability of Parts on Recognizing Handwriting Characters, Proceedings of the 16th International Graphonomics Society Conference (IGS 2013, Nara, Japan), 66.0-69.0, 2013.08.
77. Song Wang, Seiichi Uchida and Marcus Liwicki, Part-Based Recognition of Arbitrary Fonts, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 170.0-174.0, 2013.08.
78. Masanori Goto, Ryosuke Ishida, Yaokai Feng and Seiichi Uchida, Analyzing the Distribution of a Large-scale Character Pattern Set
Using Relative Neighborhood Graph, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 3.0-7.0, 2013.08.
79. Yugo Terada, Rong Huang, Yaokai Feng and Seiichi Uchida, On the Possibility of Structure Learning-Based Scene Character Detector, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 472.0-476.0, 2013.08.
80. Takashi Kimura, Rong Huang, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise, Reading-life Log - Technologies to Recognize Texts That We Read, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 91.0-95.0, 2013.08.
81. Rong Huang, Palaiahnakote Shivakumara and Seiichi Uchida, Scene Character Detection by an Edge-Ray Filter, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 462.0-466.0, 2013.08.
82. Dimosthenis Karatzas, Faisal Shafait, Seiichi Uchida, Masakazu Iwamura, Lluis Gomez i Bigorda, Sergi Robles Mestre, Joan Mas, David Fernandez Mota, Jon Almazan Almazan, Lluis Pere de las Heras, ICDAR 2013 Robust Reading Competition, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 1484.0-1493.0, 2013.08.
83. Renwu Gao, Faisal Shafait, Seiichi Uchida and Yaokai Feng, Saliency inside Saliency - A Hierarchical Usage of Visual Saliency for
Scene Character Detection, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 2013.08.
84. Chihiro Nakamoto, Rong Huang, Sota Koizumi, Ryosuke Ishida, Yaokai Feng and Seiichi Uchida, Font Distribution Analysis by Network, Proceedings of The 12th International Conference on Document Analysis and Recognition (ICDAR 2013, Washington DC, USA), 2013.08.
85. Song Wang, Seiichi Uchida, Marcus Liwicki, Yaokai Feng, Part-Based Methods for Handwritten Digit Recognition, Frontiers of Computer Science, 10.1007/s11704-013-2297-x, 7.0, 4.0, 514.0-525.0, 2013.07.
86. Soma Shiraishi, Yaokai Feng, Seiichi Uchida, Skew Estimation by Parts, IEICE Transactions on Information & Systems, 2013.07.
87. Seiichi Uchida, Image Processing and Recognition for Biological Images, Development Growth and Differentiation, 2013.05.
88. Rong Huang, Kyung hyune Rhee and Seichi Uchida, A Parallel Image Encryption Method Based on Compressive Sensing, Multimedia Tools and Applications, 2012.12.
89. Song Wang, Seiichi Uchida, and Marcus Liwicki, Part-Based Method on Handwritten Texts, Proceedings of the 21st International Conference on Pattern Recognition, 2012.11.
90. Rong Huang, Shinpei Oba, Shivakumara Palaiahnakote, and Seiichi Uchida, Scene Character Detection and Recognition Based on Multiple Hypotheses Framework (PDF), Proceedings of the 21st International Conference on Pattern Recognition, 2012.11.
91. Seiichi Uchida, Masahiro Fukutomi, Koichi Ogawara, and Yaokai Feng, Non-Markovian Dynamic Time Warping, Proceedings of the 21st International Conference on Pattern Recognition, 2012.11.
92. Seiichi Uchida, Satoshi Hokahori, and Yaokai Feng, Analytical Dynamic Programming Matching, Proceedings of the Fifth Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment, 2012.09.
93. Minoru Mori, Seiichi Uchida and Hitoshi Sakano, Dynamic Programming Matching with Global Features for Online Character Recognition, Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, 2012.09.
94. Yutaro Iwakiri, Soma Shiraishi, Yaokai Feng and Seiichi Uchida, On the Possibility of Instance-Based Stroke Recovery, Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, 2012.09.
95. Seiichi Uchida, Ryosuke Ishida, Akira Yoshida, Wenjie Cai and Yaokai Feng, Character Image Patterns as Big Data, Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, 2012.09.
96. Y. Furusawa, M. Imanishi, S. Hirata, S. Uchida, K. Nakano, K. Hayashi, Fluorescence Sensing Film for Odor Imaging, Proceedings of the 6th Asia-Pacific Conference on Transducers and Micro/Nano Technologies, 2012.07.
97. Asif Shahab, Faisal Shafait, Andreas Dengel and Seiichi Uchida, How Salient is Scene Text?, Proceedings of The 10th IAPR International Workshop on Document Analysis Systems (DAS2012, Gold Coast, Australia), 2012.03.
98. Wang Song, Marcus Liwicki, and Seiichi Uchida, Toward Part-based Document Image Decoding, Proceedings of The 10th IAPR International Workshop on Document Analysis Systems (DAS2012, Gold Coast, Australia), 2012.03.
99. Soma Shiraishi, Yaokai Feng and Seiichi Uchida, A Part-Based Skew Estimation Method, Proceedings of The 10th IAPR International Workshop on Document Analysis Systems (DAS2012, Gold Coast, Australia), 2012.03.
100. Minoru Mori, Seiichi Uchida and Hitoshi Sakano, How Important Is Global Structure for Characters?, Proceedings of The 10th IAPR International Workshop on Document Analysis Systems (DAS2012, Gold Coast, Australia), 2012.03.
101. Soma Shiraishi, Yaokai Feng and Seiichi Uchida, Part-Based Skew Estimation for Mathematical Expressions, Proceedings of The International Workshop on "Digitization and E-Inclusion in Mathematics and Science 2012 (DEIMS12, Tokyo, Japan), 2012.02.
102. Hirotaka Matsuo, Yudai Furusawa, Masashi Imanishi, Seiichi Uchida, and Kenshi Hayashi, Optical Odor Imaging by Fluorescence Probes, Journal of Robotics and Mechatoronics, 2012.01.
103. Seiichi Uchida, Wenjie Cai, Akira Yoshida, Yaokai Feng, Watching Pattern Distribution via Massive Character Recognition, 2011 IEEE International Workshop on Machine Learning for Signal Processing (MLSP2011, Beijing, China), 2011.09.
104. Seiichi Uchida, Toru Sasaki and Yaokai Feng, A Generative Model for Handwritings Based on Enhanced Feature Desynchronization, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
105. Yasuhiro Kunishige, Yaokai Feng and Seiichi Uchida, Scenery Character Detection with Environmental Context, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
106. Song Wang, Seiichi Uchida and Marcus Liwicki, Look Inside the World of Parts of Handwritten Characters, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
107. Song Wang, Seiichi Uchida and Marcus Liwicki, Comparative Study of Part-Based Handwritten Character Recognition Methods, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
108. Seiichi Uchida, Yuki Shigeyoshi, Yasuhiro Kunishige and Yaokai Feng, A Keypoint-Based Approach Toward Scenery Character Detection, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
109. Marcus Liwicki, Yoshida Akira, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise, Reliable Online Stroke Recovery from Offline Data with the Data-Embedding Pen, Proceedings of The 11th International Conference on Document Analysis and Recognition (ICDAR 2011, Beijing, China), 2011.09.
110. A. Nedzved, O. Nedzved, Sergey Ablameyko, Seiichi Uchida, Object Extraction at Nano-Surface Images, Proceedings of The Eleventh International Conference on Pattern Recognition and Information Processing (PRIP2011, Minsk, Belarus), 2011.05.
111. Wenjie Cai, Yaokai Feng and Seiichi Uchida, Massive Character Recognition with a Large Ground-Truthed Database, Proceedings of 26th Symposium On Applied Computing, 2011.03.
112. Seiichi Uchida, Ikko Fujimura, Hiroki Kawano, Yaokai Feng, Analytical Dynamic Programming Tracker, Proceedings of 10th Asian Conference on Computer Vision, 2010.11.
113. Akihiro Mori, Seiichi Uchida, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomu Hasegawa, Automatic Construction of Gesture Network for Gesture Recognition, Proceedings of IEEE TENCON2010, 2010.11.
114. Wenjie Cai, Seiichi Uchida, Hiroaki Sakoe, Toward Forensics by Stroke-Order Variation --- Performance Evaluation of Stroke Correspondence Methods, Proceedings of 4th International Workshop on Computational Forensics, 2010.11.
115. Seiichi Uchida and Marcus Liwicki, Part-Based Recognition of Handwritten Characters, Proceedings of The 12th International Conference on Frontiers in Handwriting Recognition, 2010.11.
116. Marcus Liwicki, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise, Embedding Meta-Information in Handwriting — Reed-Solomon for Reliable Error Correction, Proceedings of The 12th International Conference on Frontiers in Handwriting Recognition, 2010.11.
117. Kazumasa Iwata, Koichi Kise, Masakazu Iwamura, Seiichi Uchida and Shinichiro Omachi, Tracking and Retrieval of Pen Tip Positions for an Intelligent Camera Pen, Proceedings of The 12th International Conference on Frontiers in Handwriting Recognition, 2010.11, This paper presents a method of recovering digital ink for an intelligent camera pen, which is characterized by the functions that (1) it works on ordinary paper and (2) if an electronic document is printed on the paper the recovered digital ink is associated with the document. Two technologies called paper fingerprint and document image retrieval are integrated for realizing the above functions. The key of the integration is the introduction of image mosaicing and fast retrieval of previously seen fingerprints based on hashing of SURF local features. From the experimental results of 50 handwritings, we have confirmed that the proposed method is effective to recover and locate the digital ink from the handwriting on a physical paper..
118. Toru Wakahara and Seiichi Uchida, Hierarchical Decomposition of Handwriting Deformation Vector Field for Improving Recognition Accuracy, Proceedings of The 20th International Conference on Pattern Recognition, 2010.08.
119. Seiichi Uchida and Marcus Liwicki, Analysis of Local Features for Handwritten Character Recognition, Proceedings of The 20th International Conference on Pattern Recognition, vol.129, no.5, 2010.08.
120. Koichi Kise, Megumi Chikano, Kazumasa Iwata, Masakazu Iwamura, Seiichi Uchida and Shinichiro Omachi, Expansion of Queries and Databases for Improving the Retrieval Accuracy of Document Portions, Proceedings of The Ninth International Workshop on Document Analysis Systems, 2010.06.
121. Marcus Liwicki, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise, Data-Embedding Pen - Augmenting Ink Strokes with Meta-Information, Proceedings of The Ninth International Workshop on Document Analysis Systems, 2010.06.
122. Akio Fujiyoshi, Masakazu Suzuki and Seiichi Uchida, Grammatical Verification for Mathematical Formula Recognition Based on Context-Free Tree Grammar, Mathematics in Computer Science, vol.10, no.4, pp.559-567, 2010.03.
123. Walaa Aly, Seiichi Uchida and Masakazu Suzuki, Extract Baseline Information Using Support Vector Machine, Proceedings of The 9th Asian Symposium on Computer Mathematics, 2009.12.
124. Walaa Aly, Seiichi Uchida, and Masakazu Suzuki, Automatic Classification of Spatial Relationships among Mathematical Symbols Using Geometric Features, IEICE Trans. Information & Systems, vol. -D, 2009.11.
125. Toru Wakahara, Seiichi Uchida, Hierarchical Decomposition of Handwriting Deformation Vector Field Using 2D Warping and Global/Local Affine Transformation, Proceedings of The 10th International Conference on Document Analysis and Recognition, vol.J91-D, no.8, 2009.07.
126. Yoshinori Katayama, Seiichi Uchida and Hiroaki Sakoe,, Stochastic Model of Stroke Order Variation, Proceedings of The 10th International Conference on Document Analysis and Recognition, 2009.07.
127. Kazumasa Iwata, Koichi Kise, Tomohiro Nakai, Masakazu Iwamura, Seiichi Uchida and Shinichiro Omachi,, Capturing Digital Ink as Retrieving Fragments of Document Images, Proceedings of The 10th International Conference on Document Analysis and Recognition, vol.29, no.9, pp.1326-1332, 2009.07.
128. Akio Fujiyoshi, Masakazu Suzuki and Seiichi Uchida,, Syntactic Detection and Correction of Misrecognitions in Mathematical OCR, Proceedings of The 10th International Conference on Document Analysis and Recognition, 2009.07.
129. Seiichi Uchida, Ryoji Hattori, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise,, Conspicuous character patterns, Proceedings of The 10th International Conference on Document Analysis and Recognition, vol.J91-D, no.5, pp.1434-1441, 2009.07.
130. Walaa Aly, Seiichi Uchida, Akio Fujiyoshi and Masakazu Suzuki,, Statistical classification of spatial relationships among mathematical symbols, Proceedings of The 10th International Conference on Document Analysis and Recognition, vol.J91-D, no.5, pp.1380-1392, 2009.07.
131. Koichi Kise, Kazumasa Iwata, Tomohiro Nakai, Masakazu Iwamura, Seiichi Uchida and Shinichiro Omachi, Document-Level Positioning of a Pen Tip by Retrieval of Image Fragments, Proceedings of The Third International Workshop on Camera-Based Document Analyais and Recognition, vol.41, no.4, pp.1230-1240, 2009.07.
132. Seiichi Uchida, Ryoji Hattori, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise?, Selecting and Evaluating Conspicuous Character Patterns, Proceedings of The Third International Workshop on Camera-Based Document Analyais and Recognition, 25OF4-N52, 2009.07.
133. Seiichi Uchida, Katsuhiro Itou, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise?, On a Possibility of Pen-Tip Camera for the Reconstruction of Handwritings, Proceedings of The Third International Workshop on Camera-Based Document Analyais and Recognition, vol.J91-D, no.1, pp.136-138, 2009.07.
134. Masakazu Iwamura, Ryo Niwa, Akira Horimatsu, Koichi Kise, Seiichi Uchida, and Shinichiro Omachi, Layout-Free Dewarping of Planar Document Images, Document Recognition and Retrieval XVI, 2009.01.
135. Seiichi Uchida, Kazuma Amamoto,, Early Recognition of Sequential Patterns by Classifier Combination, Proceedings of 19th IAPR International Conference on Pattern Recognition (ICPR 2008), vol.7, no.4, pp.709-733, Oct. 2007., 2008.12.
136. Yoshinori Katayama, Seiichi Uchida, and Hiroaki Sakoe,, A New HMM for On-Line Character Recognition Using Pen-Direction and Pen-Coordinate Features, Proceedings of 19th IAPR International Conference on Pattern Recognition (ICPR 2008), 2008.12.
137. Walaa Aly, Seiichi Uchida, and Masakazu Suzuki, Identifying subscripts and superscripts in mathematical documents, Mathematics in Computer Science, 2008.12.
138. Akihiro Mori and Seiichi Uchida, Fast image mosaicing based on histograms, IEICE Transactions on Information and Systems, 2008.11.
139. Seiichi Uchida, Megumi Sakai, Masakazu Iwamura, Shinichiro Omachi, and Koichi Kise,, Skew Estimation by Instances, Proceedings of The Eighth International Workshop on Document Analysis Systems, 2008.09.
140. Akira Horimatsu, Ryo Niwa, Masakazu Iwamura, Koichi Kise, Seiichi Uchida, and Shinichiro Omachi,, Affine Invariant Recognition of Characters by Progressive Pruning, Proceedings of The Eighth International Workshop on Document Analysis Systems, 2008.09.
141. Walaa Aly, Seiichi Uchida, and Masakazu Suzuki,, A Large-Scale Analysis of Mathematical Expressions for an Accurate Understanding of Their Structure, Proceedings of The Eighth International Workshop on Document Analysis Systems, 2008.09.
142. Ken'ichi Morooka, Xian Chen, Ryo Kurazume, Uchida Seiichi, Kenji Hara, Yumi Iwashita, Makoto Hashizume, Real-time Nonlinear FEM with Neural Network for Simulating Soft Organ Model Deformation, Proceedings of The 11th International Conference on Medical Image Computing and Computer Assisted Intervention, 2008.09.
143. Seiichi Uchida, Kazuya Niyagawa, Hiroaki Sakoe,, Feature Desynchronization in Online Character Recognition, Proceedings of the 11th International Conference on Frontiers of Handwriting Recognition, 2008.08.
144. Akio Fujiyoshi, Masakazu Suzuki, Seiichi Uchida,, Verification of Mathematical Formulae Based on a Combination of Context-Free Grammar and Tree Grammar, Proceedings of The Seventh International Conference on Mathematical Knowledge Management, 2008.07.
145. Christopher D. Malon, Seiichi Uchida, Masakazu Suzuki, Mathematical symbol recognition with support vector machines, Pattern Recognition Letters, 2008.07.
146. Yumi Iwashita, Ryo Kurazume, Kenji Hara, Seiichi Uchida, Ken'ichi Morooka, Tsutomu Hasegawa,, Fast 3D Reconstruction of Human Shape and Motion Tracking by Parallel Fast Level Set Method, Proceedings of 2008 IEEE International Conference on Robotics and Automation, 2008.05.
147. Seiichi Uchida, Hiromitsu Miyazaki, Hiroaki Sakoe, Mosaicing-by-recognition for video-based text recognition, Pattern Recognition, vol.24, no.8, pp.954--963, 2008.04.
148. Yuji Shinomura, Tomotaka Harano, Toru Tamaki, Toshiyuki Amano, Kazufumi Kaneda, Seiichi Uchida,, Comparative study of path nomalizations for path prediction, Proceedings of 14th Korea-Japan Joint Workshop on Frontiers of Computer Vision, pp.61-66, 2008.01.
149. Seiichi Uchida, Akihiro Mori, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomu Hasegawa,, Logical DP Matching for Detecting Similar Subsequence, Proceedings of 8th Asian Conference on Computer Vision, 2007.11.
150. Sergey V. Ablameyko, Seiichi Uchida, Recognition of engineering drawing entities: review of approaches, International Journal of Image and Graphics, 2007.10.
151. Victor Bucha, Sergey Ablameyko, Seiichi Uchida, Image pixel force fields and their application for color map vectorisation, Proceedings of 9th International Conference on Document Analysis and Recognition, 2007.09.
152. Daiki Baba, Seiichi Uchida, Hiroaki Sakoe, Predictive DP Matching for On-Line Character Recognition, Proceedings of 9th International Conference on Document Analysis and Recognition, 2007.09.
153. Seiichi Uchida, Megumi Sakai, Masakazu Iwamura, Shinichiro Omachi, Koichi Kise, Extraction of Embedded Class Information from Universal Character Pattern, Proceedings of 9th International Conference on Document Analysis and Recognition, 2007.09, This paper is concerned with a universal pattern, which
is defined as a character pattern designed to have high
machine-readability. This universal pattern is a character
pattern printed with stripes. The cross ratio calculated
from the widths of the stripes represents the character class.
Thus, if the boundaries of the stripes can be detected for
measuring the widths, the class can be determined without
ordinary recognition process. Furthermore, since the cross
ratio is invariant to projective distortions, the correct class
will be still determined under those distortions. This paper
describes a practical scheme to recognize this universal
pattern. The proposed scheme includes a novel algorithm to
detect the stripe boundaries stably even from the universal
pattern image contaminated by non-uniform lighting and
noise. The algorithm is realized by a combination of a dynamic
programming-based optimal boundary detection and
a finite state automaton which represents the property of
the universal pattern. Experimental results showed the proposed
scheme could recognize 99.6% of the universal pattern
images which underwent heavy projective distortions
and non-uniform lighting..
154. Roman Bertolami, Seiichi Uchida, Matthias Zimmermann, Horst Bunke,, Non-Uniform Slant Correction for Handwritten Text Line Recognition, Proceedings of 9th International Conference on Document Analysis and Recognition, 2007.09.
155. Masakazu Iwamura, Ryo Niwa, Koichi Kise, Seiichi Uchida, Shinichiro Omachi,, Rectifying Perspective Distortion into Affine Distortion Using Variants and Invariants, Proceedings of Second International Workshop on Camera-Based Document Analysis and Recognition 2007, 2007.09.
156. Seiichi Uchida, Megumi Sakai, Masakazu Iwamura, Shinichiro Omachi, Koichi Kise,, Instance-Based Skew Estimation of Document Images by a Combination of Variant and Invariant, Proceedings of Second International Workshop on Camera-Based Document Analysis and Recognition 2007, 2007.09.
157. Ryoji Hattori, Seiichi Uchida, Color quantization for scene change detection, Proceedings of The First International Symposium on Information and Computer Elements, 2007.09.
158. Atsutoshi Shimeno, Seiichi Uchida, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomu Hasegawa, Separation and tracking of moving object using rough motion information from the object, Proceedings of The First International Symposium on Information and Computer Elements, Document Analysis Systems VII, Lecture Notes in Computer Sciences 3872, pp.153-163, 2006, 2007.09.
159. Ken'ichi Morooka, Hiroshi Masuda, Ryo Kurazume, Xian Chen, Seiichi Uchida, Kenji Hara, Makoto Hashizume, Real time estimation of deforming organs by neural network for endoscopic surgery simulator, Proceedings of The First International Symposium on Information and Computer Elements, vol.J89-D, no.2, pp.344--352, 2007.09.
160. Masakazu Suzuki, Christopher Malon, Seiichi Uchida, Databases of mathematical documents, Research Reports on Information Science and Electrical Engineering of Kyushu University, 302-306, 2007.04.
161. Masato Nakajima, Seiichi Uchida, Akihiro Mori, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomu Hasegawa, Hiroaki Sakoe, Motion prediction based on eigen-gestures, Proceedings of the 1st First Korea-Japan Joint Workshop on Pattern Recognition, 904-908, 2006.11.
162. Masakazu Iwamura, Yoshio Furuya, Koichi Kise, Shinichiro Omachi, Seiichi Uchida, Better decision boundary for pattern recognition with supplementary information, Proceedings of the 1st First Korea-Japan Joint Workshop on Pattern Recognition, E88D, 8, 1781-1790, 2006.11.
163. Seiichi Uchida, Kazuhiro Tanaka, Masakazu Iwamura, Shinichiro Omachi, and Koichi Kise, A data-embedding pen, Proceedings of the 10th International Workshop on Frontiers of Handwriting Recognition (IWFHR-10), 2006.10.
164. Y.Araki, D.Arita, R.Taniguchi, S.Uchida, R.Kurazume and T.Hasegawa, Construction of symbolic representation from human motion information, 10th Int. Conf. on Knowledge-Based & Intelligent Information & Engineering Systems, 2006.10.
165. Shinichiro Omachi, Masakazu Iwamura, Seiichi Uchida, and Koichi Kis, Affine invariant information embedment for accurate camera-based character recognition, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), vol. 36, no. 5, pp. 13-22, 2006.08.
166. Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi, and Koichi Kise, OCR fonts revisited for camera-based character recognition, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), 2006.08.
167. Ryo Kurazume, Hiroaki Omasa, Seiichi Uchida, Rin-ichiro Taniguchi, and Tsutomu Hasegawa, Embodied Proactive Human Interface ''PICO-2'', Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), pp.80-85, 2006.08.
168. Akihiro Mori, Seiichi Uchida, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomu Hasegawa and Hiroaki Sakoe, Early recognition and prediction of gestures, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), 情報処理学会九州支部 推薦論文, 2006.08.
169. Wenjie Cai, Seiichi Uchida, Hiroaki Sakoe, An efficient radical-based algorithm for stroke-order-free online Kanji character recognition, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), 3-8, 2006.08.
170. V.Bucha, S.Uchida, S.Ablameyko, Interactive Road Extraction with Pixel Force Fields, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), 2006.08.
171. A.Nedzved, S.Uchida, S.Ablameyko, Gray-scale thinning by using a pseudo-distance map, Proceedings of 18th IAPR International Conference on Pattern Recognition (ICPR 2006), 224-227, 2006.08.
172. Christopher D. Malon, Seiichi Uchida, and Masakazu Suzuki, Support Vector Machines for Mathematical Symbol Recognition, 6th International Workshop on Statistical Pattern Recognition, 2006.08.
173. Seiichi Toyota, Seiichi Uchida, and Masakazu Suzuki, Structural Analysis of Mathematical Formulae with Verification Based on Formula Description Grammar, Proceedings of 7th IAPR Workshop on Document Analysis Systems, 2006.02.
174. Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi and Koichi Kise, Data Embedding for Camera-Based Character Recognition, First International Workshop on Camera-Based Document Analysis and Recognition 2005 (CBDAR 2005, Seoul, Korea), 2005.08.
175. Masakazu Iwamura, Seiichi Uchida, Shinichiro Omachi and Koichi Kise, Recognition with Supplementary Information ---How Many Bits Are Lacking for 100% Recognition?---, First International Workshop on Camera-Based Document Analysis and Recognition 2005 (CBDAR 2005, Seoul, Korea), 2005.08.
176. Seiichi Uchida, Hiromitsu Miyazaki, and Hiroaki Sakoe, Mosaicing-by-recognition for recognizing texts captured in multiple video frames, First International Workshop on Camera-Based Document Analysis and Recognition 2005 (CBDAR 2005, Seoul, Korea), 2005.08.
177. Masakazu Suzuki, Seiichi Uchida, and Akihiro Nomura, A ground-truthed mathematical character and symbol image database, Proceedings of 8th International Conference on Document Analysis and Recognition, 10.1109/ICDAR.2005.14, 2005.08.
178. Hiroki Ezaki, Seiichi Uchida, Akira Asano, and Hiroaki Sakoe, Dewarping of document image by global optimization, Proceedings of 8th International Conference on Document Analysis and Recognition, 10.1109/ICDAR.2005.87, 2005.08.
179. Daiki Okumura, Seiichi Uchida, and Hiroaki Sakoe, An HMM implementation for on-line handwriting recognition based on pen-coordinate feature and pen-direction feature, Proceedings of 8th International Conference on Document Analysis and Recognition, 10.1109/ICDAR.2005.50, 2005.08.
180. Hiroto Mitoma, Seiichi Uchida, and Hiroaki Sakoe, Online character recognition based on elastic matching and quadratic discrimination, Proceedings of 8th International Conference on Document Analysis and Recognition, 10.1109/ICDAR.2005.178, 2005.08.
181. Hiromitsu Miyazaki, Seiichi Uchida, and Hiroaki Sakoe, Mosaicing-by-recognition: a technique for video-based text recognition, Proceedings of 8th International Conference on Document Analysis and Recognition, 10.1109/ICDAR.2005.161, 2005.08.
182. Seiichi Uchida and Hiroaki Sakoe, A survey of elastic matching techniques for handwritten character recognition, IEICE Transactions on Information & Systems, 10.1093/ietisy/e88-d.8.1781, 2005.08.
183. Seiichi Uchida, Akihiro Nomura, and Masakazu Suzuki, Quantitative analysis of mathematical documents, International Journal on Document Analysis and Recognition, 163-167, vol. 1 of 2, pp. 163-167, 2005.06.
184. Seiichi Uchida and Hiroaki Sakoe, Category-dependent elastic matching based on a linear combination of eigen-deformations, Systems and Computers in Japan, 126-130, 2005.05.
185. Akihiro Mori, Seiichi Uchida, Ryo Kurazume, Rin-ichiro Taniguchi, Tsutomo Hasegawa, and Hiroaki Sakoe, Early Recognition of Gestures, 11th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 72-77, 2005.01.
186. Hiroto Mitoma, Seiichi Uchida, and Hiroaki Sakoe, Online character recognition using eigen-deformations, the Ninth International Workshop on Frontiers of Handwriting Recognition, vol. 55, no. 12, pp. 1643-1649, 2004.10.
187. Naoki Matsumoto, Seiichi Uchida, and Hiroaki Sakoe, Prototype setting for elastic matching-based image pattern recognition, Proceedings of 17th IAPR International Conference on Pattern Recognition (ICPR 2004, Cambridge, UK),, 10.1109/ICPR.2004.1334064, 39-43, vol. 1 of 1, pp. 434--438, 2004.08.
188. R. Taniguchi, D. Arita, S. Uchida, R. Kurazume, and T. Hasegawa, Human action sensing for proactive human interface: Computer vision approach, Proceedings of International workshop on Processing Sensory Information for Proactive Systems (PSIPS 2004, Oulu, Finland), Vol.6, No..1,, 2004.06.
189. Eiji Taira, Seiichi Uchida, and Hiroaki Sakoe, Nonuniform slant correction for handwritten word recognition,, IEICE Transactions on Information & Systems, Vol.6, No..1,, 2004.05.
190. Eiji Taira, Seiichi Uchida, and Hiroaki Sakoe, Block boundary detection and title extraction for automatic bookshelf inspection, Tenth Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2005, Fukuoka, Japan), Vol.5, No..1,, 2004.02.
191. Eiji Taira, Seiichi Uchida, and Hiroaki Sakoe, A model-based book boundary detection technique for bookshelf image analysis, Asian Conference on Computer Vision (ACCV2004, Jeju Island, Korea), Vol.5, No..1,, 2004.01.
192. Eiji Taira, Seiichi Uchida, and Hiroaki Sakoe, Book boundary detection from bookshelf image based on model fitting, International Symposium on Information Science and Electrical Engineering, 534-537, 2003.11.
193. Wenjie Cai, Seiichi Uchida, and Hiroaki Sakoe, A comparative study of stroke correspondence search algorithms for online kanji character recognition, International Symposium on Information Science and Electrical Engineering, E83D, 1, 109-111, Vol.1, No.E83, pp.109-111, 2003.11.
194. Seiichi Uchida and Hiroaki Sakoe, A preliminary study of pixel-based motion compensation, International Symposium on Information Science and Electrical Engineering, pp.5, 2003.11.
195. Masakazu Suzuki, Fumikazu Tamari, Ryoji Fukuda, Seiichi Uchida, and Toshihiro Kanahori, INFTY --- An integrated OCR system for mathematical documents, ACM Symposium on Document Engineering (DocEng 2003, Grenoble, France), E82D, 3, 693-700, Vol.3, No.E82, pp.693-700, 2003.11.
196. Seiichi Uchida, Hiroaki Sakoe, Eigen-deformations for elastic matching based handwritten character recognition,, Pattern Recognition, 10.1016/S0031-3203(03)00039-6, Vol.6, No.J81, pp.1251-1258, 2003.09.
197. Seiichi Uchida and Hiroaki Sakoe, Handwritten character recognition using elastic matching based on a class-dependent deformation model, Proceedings of 7th International Conference on Document Analysis and Recognition (ICDAR 2003, Edinburgh, Scotland, 521-524, pp.14, 2003.08.
198. Akihiro Nomura, Kazuyuki Michishita, Seiichi Uchida, and Masakazu Suzuki, Detection and segmentation of touching characters in mathematical expressions, Proceedings of 7th International Conference on Document Analysis and Recognition (ICDAR 2003, Edinburgh, Scotland, Vol.1, No..1, pp.95-100, 2003.08.
199. Seiichi Uchida and Hiroaki Sakoe, A handwritten character recognition method based on unconstrained elastic matching and eigen-deformations, Proceedings of the Eighth International Workshop on Frontiers of Handwriting Recognition (IWFHR-8, Niagara-on-the-Lake, Ontario, Canada),, 2002.08.
200. Seiichi Uchida, Eiji Taira, and Hiroaki Sakoe, Nonuniform slant correction using dynamic programming, Proceedings of 6th International Conference on Document Analysis and Recognition (ICDAR 2001, Seattle, USA),, 2001.09.
201. Mohammad Asad Ronee, Seiichi Uchida, and Hiroaki Sakoe, Handwritten character recognition using piecewise linear two-dimensional warping, Proceedings of 6th International Conference on Document Analysis and Recognition (ICDAR 2001, Seattle, USA),, 2001.09.
202. R. Bogush, S. Maltsev, S. Ablameyko, S. Uchida, and S. Kamata, An efficient correlation computation method for binary images based on matrix factorisation, Proceedings of 6th International Conference on Document Analysis and Recognition (ICDAR 2001, Seattle, USA),, 2001.09.
203. S. Uchida and H. Sakoe, Piecewise Linear Two-Dimensional Warping, International Conference on Pattern Recognition, 2000.01.
204. S. Uchida and H. Sakoe, An Approximation Algorithm for Two-Dimensional Warping, IEICE Trans. Information & Systems, vol. -D, 2000.01.
205. S. Uchida and H. Sakoe, Handwritten Character Recognition Using Monotonic and Continuous Two-Dimensional Warping, Proc. th International Conference on Document Analysis and Recognition, 1999.01.
206. S. Uchida and H. Sakoe, An Efficient Two-Dimensional Warping Algorithm, IEICE Trans. Information & Systems, vol. -D, 1999.01.
207. S. Uchida and H. Sakoe, A Monotonic and Continuous Two-Dimensional Warping Based on Dynamic Programming, Proc. th International Conference on Pattern Recognition, 1998.01.