2024/03/19 更新

写真a

イシカワ ヒロシ
石川 博
所属
理工学術院 基幹理工学部
職名
教授
学位
博士(計算機科学) ( ニューヨーク大学 (米国) )
修士(理学) ( 京都大学 )
ホームページ

経歴

  • 2016年
    -
    継続中

    国立情報学研究所   客員教授(兼任)

  • 2010年
    -
    継続中

    早稲田大学   基幹理工学部情報理工学科   教授

  • 2009年
    -
    2013年

    JST   さきがけ研究者(兼任)

  • 2010年
     
     

    名古屋市立大学   大学院システム自然科学研究科   教授

  • 2005年
    -
    2010年

    名古屋市立大学   大学院システム自然科学研究科   助教授(准教授)

  • 2004年
    -
    2005年

    名古屋市立大学   大学院システム自然科学研究科   講師

  • 2000年
    -
    2001年

    ニューヨーク大学   クーラン数理科学研究所   Associate Research Scientist

▼全件表示

学歴

  •  
    -
    2000年

    ニューヨーク大学   計算機科学  

  •  
    -
    1993年

    京都大学   理学研究科   数学  

  •  
    -
    1991年

    京都大学   理学部   数学  

委員歴

  • 2020年
     
     

    European Conference on Computer Vision (ECCV2020)  Area Chair

  • 2018年
    -
    2020年

    Asian Conference on Computer Vision (ACCV2020)  Program Chair

  • 2016年
    -
    2020年

    情報処理学会 コンピュータビジョンとイメージメディア(CVIM)研究運営委員会  幹事

  • 2016年
    -
    2020年

    IPSJ Transactions on Computer Vision Applications  Associate Editor in Chief

  • 2019年
     
     

    IEEE International Conference on Computer Vision (ICCV2019)  Area Chair

  • 2018年
    -
    2019年

    Computer Graphics International 2019 (CGI’19)  Conference Co-Chair

  • 2017年
    -
    2018年

    情報処理学会 第80回全国大会 実行委員会  副委員長

  • 2016年
    -
    2018年

    画像電子学会  理事

  • 2017年
     
     

    IEEE International Conference on Computer Vision (ICCV2017)  Area Chair

  • 2016年
    -
    2017年

    Fifteenth IAPR International Conference on Machine Vision Applications (MVA2017)  General Chiar

  • 2011年
    -
    2017年

    電子情報通信学会 パターン認識・メディア理解研究会  専門委員

  • 2016年
     
     

    Asian Conference on Computer Vision (ACCV2016)  Area Chair

  • 2016年
     
     

    画像の認識・理解シンポジウム (MIRU2016) Conference Editorial Board  Editor in Chief

  • 2013年
    -
    2016年

    IEEE Transactions on Pattern Analysis and Machine Intelligence  Associate Editor

  • 2015年
     
     

    IEEE International Conference on Computer Vision (ICCV2015)  Area Chair

  • 2015年
     
     

    画像の認識・理解シンポジウム (MIRU2015) Conference Editorial Board  Associate Editor in Chief

  • 2014年
    -
    2015年

    Fourteenth IAPR International Conference on Machine Vision Applications (MVA2015)  General Chiar

  • 2012年
    -
    2015年

    IET Computer Vision  Editorial Board Member

  • 2014年
     
     

    Asian Conference on Computer Vision (ACCV2014)  Area Chair

  • 2014年
     
     

    画像の認識・理解シンポジウム (MIRU2014) Conference Editorial Board  Associate Editor in Chief

  • 2013年
    -
     

    IEICE MI: Medical Imaging  Expert Committee Member

  • 2013年
    -
     

    電子情報通信学会 医用画像研究会  専門委員

  • 2013年
     
     

    画像の認識・理解シンポジウム(MIRU2013)  Area Chair

  • 2013年
     
     

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013)  Area Chair

  • 2011年
    -
    2013年

    International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2011, 2013)  Program Committee Member

  • 2010年
    -
    2013年

    IPSJ Transactions on Computer Vision Applications  Associate Editor

  • 2009年
    -
    2012年

    IEICE Transactions on Information and Systems  Editorial Board Member

  • 2009年
    -
    2012年

    電子情報通信学会和文論文誌D  編集委員

  • 2008年
    -
    2012年

    IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV2008, 2010, 2012)  Program Committee Member

  • 2011年
     
     

    画像の認識・理解シンポジウム(MIRU2011)  Area Chair

  • 2011年
     
     

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR2011)  Area Chair

  • 2007年
    -
    2011年

    IEEE International Conference on Computer Vision (ICCV 2007, 2009, 2011)  Program Committee Member

  • 2010年
    -
     

    International Journal of Computer Vision  Editorial Board Member

  • 2010年
     
     

    Asian Conference on Computer Vision (ACCV2010)  Program Committee Member

  • 2010年
     
     

    画像の認識・理解シンポジウム(MIRU2010)  Area Chair

  • 2008年
    -
    2010年

    European Conference on Computer Vision (ECCV 2008, 2010)  Program Committee Member

  • 2007年
    -
    2010年

    IPSJ SIG-CVIM: Computer Vision and Image Media  Organizing Committee Member

  • 2007年
    -
    2010年

    情報処理学会 コンピュータビジョンとイメージメディア(CVIM)研究運営委員会  運営委員

  • 2009年
     
     

    画像の認識・理解シンポジウム(MIRU2009)  Area Chair

  • 2008年
     
     

    Short Program: Graph Cuts and Related Discrete or Continuous Optimization Problems at IPAM, UCLA.  Organizing Committee Member

  • 2008年
     
     

    International Conference on Pattern Recognition (ICPR2008)  Program Committee Member

  • 2008年
     
     

    画像の認識・理解シンポジウム(MIRU2008)  Area Chair

  • 2006年
    -
    2007年

    Tenth IAPR Conference on Machine Vision Applications (MVA2007).  Local Arrangement Chair

  • 2005年
    -
     

    IAPR Conference on Machine Vision Applications(MVA)  Organizing Committee Member

▼全件表示

所属学協会

  •  
     
     

    ACM

  •  
     
     

    IEEE

  •  
     
     

    電子情報通信学会

  •  
     
     

    情報処理学会

研究分野

  • 知能ロボティクス

研究キーワード

  • 人工知能、ディープラーニング

  • コンピュータービジョン、離散最適化、パターン解析

受賞

  • 第75回電子情報通信学会論文賞

    2019年06月   電子情報通信学会  

  • Innovative Technologies 2016特別賞「Culture」

    2016年10月   経済産業省  

  • MIRU長尾賞(最優秀論文賞)

    2009年07月  

  • Young Author Award

    2006年12月   IEEE Computer Society Japan Chapter  

  • MIRU2006 優秀論文賞

    2006年07月  

  • Harold Grad Memorial Prize

    2000年04月   Courant Institute of Mathematical Sciences, New York University  

▼全件表示

 

論文

  • Optimization-Based Data Generation for Photo Enhancement

    M. Omiya, Y. Horiuchi, E. Simo-Serra, S. Iizuka, H. Ishikawa

    New Trends in Image Restoration and Enhancement Workshop (NITRE2019) at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2019)    2019年06月  [査読有り]

  • Temporal Distance Matrices for Squat Classification

    R. Ogata, E. Simo-Serra, S. Iizuka, H. Ishikawa

    Fifth International Workshop on Computer Vision in Sports (CVsports) at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2019)    2019年06月  [査読有り]

  • Re-staining Pathology Images by FCNN

    M. Fujitani, Y. Mochizuki, S. Iizuka, E. Simo-Serra, H. Kobayashi, C. Iwamoto, K. Ohuchida, M. Hashizume, H. Hontani, H. Ishikawa

    The 16th International Conference on Machine Vision Applications (MVA 2019)    2019年05月  [査読有り]

    DOI

    Scopus

    7
    被引用数
    (Scopus)
  • Spectral Normalization and Relativistic Adversarial Training for Conditional Pose Generation with Self-Attention

    Y. Horiuchi, E. Simo-Serra, S. Iizuka, H. Ishikawa

    The 16th International Conference on Machine Vision Applications (MVA 2019)    2019年05月  [査読有り]

    DOI

    Scopus

    6
    被引用数
    (Scopus)
  • Learning Photo Enhancement by Black-Box Model Optimization Data Generation

    M. Omiya, E. Simo-Serra, S. Iizuka, H. Ishikawa

    SIGGRAPH Asia 2018 Technical Briefs    2018年12月  [査読有り]

    DOI

    Scopus

    6
    被引用数
    (Scopus)
  • Real-Time Data-Driven Interactive Rough Sketch Inking

    E. Simo-Serra, S. Iizuka, H. Ishikawa

    ACM Transactions on Graphics (Proc. of SIGGRAPH2018)   37 ( 4 )  2018年08月  [査読有り]

    DOI

    Scopus

    40
    被引用数
    (Scopus)
  • 高階グラフカットによる医用画像領域分割

    石川 博, 北村嘉郎

    画像ラボ   ( 2018年7月号 ) 21 - 26  2018年07月

  • Learning to restore deteriorated line drawing

    Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

    Visual Computer   34 ( 6-8 ) 1077 - 1085  2018年06月  [査読有り]

     概要を見る

    We propose a fully automatic approach to restore aged old line drawings. We decompose the task into two subtasks: the line extraction subtask, which aims to extract line fragments and remove the paper texture background, and the restoration subtask, which fills in possible gaps and deterioration of the lines to produce a clean line drawing. Our approach is based on a convolutional neural network that consists of two sub-networks corresponding to the two subtasks. They are trained as part of a single framework in an end-to-end fashion. We also introduce a new dataset consisting of manually annotated sketches by Leonardo da Vinci which, in combination with a synthetic data generation approach, allows training the network to restore deteriorated line drawings. We evaluate our method on challenging 500-year-old sketches and compare with existing approaches with a user study, in which it is found that our approach is preferred 72.7% of the time.

    DOI

    Scopus

    13
    被引用数
    (Scopus)
  • Flooding-based segmentation for contactless hand biometrics oriented to mobile devices

    Gonzalo Bailador, Belén Ríos-Sánchez, Raúl Sánchez-Reillo, Hiroshi Ishikawa, Carmen Sánchez-Ávila

    IET Biometrics   7 ( 5 ) 431 - 438  2018年05月  [査読有り]

    DOI

    Scopus

    4
    被引用数
    (Scopus)
  • Multi-label Fashion Image Classification with Minimal Human Supervision

    Naoto Inoue, Edgar Simo-Serra, Toshihiko Yamasaki, Hiroshi Ishikawa

    Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017   2018-   2261 - 2267  2018年01月  [査読有り]

     概要を見る

    We tackle the problem of multi-label classification of fashion images, learning from noisy data with minimal human supervision. We present a new dataset of full body poses, each with a set of 66 binary labels corresponding to the information about the garments worn in the image obtained in an automatic manner. As the automatically-collected labels contain significant noise, we manually correct the labels for a small subset of the data, and use these correct labels for further training and evaluation. We build upon a recent approach that both cleans the noisy labels and learns to classify, and introduce simple changes that can significantly improve the performance.

    DOI

    Scopus

    43
    被引用数
    (Scopus)
  • What Makes a Style: Experimental Analysis of Fashion Prediction

    Moeko Takagi, Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa

    Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017   2018-   2247 - 2253  2018年01月  [査読有り]

     概要を見る

    In this work, we perform an experimental analysis of the differences of both how humans and machines see and distinguish fashion styles. For this purpose, we propose an expert-curated new dataset for fashion style prediction, which consists of 14 different fashion styles each with roughly 1,000 images of worn outfits. The dataset, with a total of 13,126 images, captures the diversity and complexity of modern fashion styles. We perform an extensive analysis of the dataset by benchmarking a wide variety of modern classification networks, and also perform an in-depth user study with both fashion-savvy and fashion-naïve users. Our results indicate that, although classification networks are able to outperform naive users, they are still far from the performance of savvy users, for which it is important to not only consider texture and color, but subtle differences in the combination of garments.

    DOI

    Scopus

    41
    被引用数
    (Scopus)
  • Mastering sketching: Adversarial augmentation for structured prediction

    Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa

    ACM Transactions on Graphics   37 ( 1 )  2018年01月  [査読有り]

     概要を見る

    We present an integral framework for training sketch simplification networks that convert challenging rough sketches into clean line drawings. Our approach augments a simplification network with a discriminator network, training both networks jointly so that the discriminator network discerns whether a line drawing is real training data or the output of the simplification network, which, in turn, tries to fool it. This approach has two major advantages: first, because the discriminator network learns the structure in line drawings, it encourages the output sketches of the simplification network to be more similar in appearance to the training sketches. Second, we can also train the networks with additional unsupervised data: by adding rough sketches and line drawings that are not corresponding to each other, we can improve the quality of the sketch simplification. Thanks to a difference in the architecture, our approach has advantages over similar adversarial training approaches in stability of training and the aforementioned ability to utilize unsupervised training data. We show how our framework can be used to train models that significantly outperform the state of the art in the sketch simplification task, despite using the same architecture for inference. We also present an approach to optimize for a single image, which improves accuracy at the cost of additional computation time. Finally, we show that, using the same framework, it is possible to train the network to perform the inverse problem, i.e., convert simple line sketches into pencil drawings, which is not possible using the standard mean squared error loss. We validate our framework with two user tests, in which our approach is preferred to the state of the art in sketch simplification 88.9% of the time.

    DOI

    Scopus

    83
    被引用数
    (Scopus)
  • 高階エネルギー最小化による医用画像セグメンテーション

    北村嘉郎, 石川博

    電子情報通信学会 和文論文誌D   J101-D ( 1 ) 3 - 26  2018年01月  [査読有り]  [招待有り]

    DOI

  • 画像類似度を考慮したデータセットを用いて学習したCNNによる病理画像の染色変換 (医用画像)

    藤谷 真之, 望月 義彦, 飯塚 里志, シモセラ エドガー, 石川 博

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   117 ( 281 ) 9 - 14  2017年11月

    CiNii

  • Adaptive Energy Selection for Content-Aware Image Resizing

    K. Sasaki, Y. Nagahama, Z. Ze, S. Iizuka, E. Simo-Serra, Y. Mochizuki, H. Ishikawa

    Fourth Asian Conference on Pattern Recognition (ACPR2017)    2017年11月  [査読有り]

  • 人工知能で白黒写真をカラーに

    石川 博

    画像ラボ   ( 2017年10月号 ) 14 - 21  2017年10月

  • Banknote portrait detection using convolutional neural network

    Ryutaro Kitagawa, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Matsuki, Naotake Natori, Hiroshi Ishikawa

    Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017     440 - 443  2017年07月  [査読有り]

     概要を見る

    Banknotes generally have different designs according to their denominations. Thus, if characteristics of each design can be recognized, they can be used for sorting banknotes according to denominations. Portrait in banknotes is one such characteristic that can be used for classification. A sorting system for banknotes can be designed that recognizes portraits in each banknote and sort it accordingly. In this paper, our aim is to automate the configuration of such a sorting system by automatically detect portraits in sample banknotes, so that it can be quickly deployed in a new target country. We use Convolutional Neural Networks to detect portraits in completely new set of banknotes robust to variation in the ways they are shown, such as the size and the orientation of the face.

    DOI

    Scopus

    8
    被引用数
    (Scopus)
  • Unsupervised video object segmentation by supertrajectory labeling

    Masahiro Masuda, Yoshihiko Mochizuki, Hiroshi Ishikawa

    Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017     448 - 451  2017年07月  [査読有り]

     概要を見る

    We propose a novel approach to unsupervised video segmentation based on the trajectories of Temporal Super-pixels (TSPs). We cast the segmentation problem as a trajectory-labeling problem and define a Markov random field on a graph in which each node represents a trajectory of TSPs, which we minimize using a new two-stage optimization method we developed. The adaption of the trajectories as basic building blocks brings several advantages over conventional superpixel-based methods, such as more expressive potential functions, temporal coherence of the resulting segmentation, and drastically reduced number of the MRF nodes. The most important effect is, however, that it allows more robust segmentation of the foreground that is static in some frames. The method is evaluated on a subset of the standard SegTrack benchmark and yields competitive results against the state-of-the-art methods.

    DOI

    Scopus

    1
    被引用数
    (Scopus)
  • Multiple-organ segmentation by graph cuts with supervoxel nodes

    Toshiya Takaoka, Yoshihiko Mochizuki, Hiroshi Ishikawa

    Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017     424 - 427  2017年07月  [査読有り]

     概要を見る

    Improvement in medical imaging technologies has made it possible for doctors to directly look into patients' bodies in ever finer details. However, since only the cross-sectional image can be directly seen, it is essential to segment the volume into organs so that their shape can be seen as 3D graphics of the organ boundary surfaces. Segmentation is also important for quantitative measurement for diagnosis. Here, we introduce a novel higher-precision method to segment multiple organs using graph cuts within medical images such as CT-scanned images. We utilize super voxels instead of voxels as the units of segmentation, i.e., the nodes in the graphical model, and design the energy function to minimize accordingly. We utilize SLIC super voxel algorithm and verify the performance of our segmentation algorithm by energy minimization comparing to the ground truth.

    DOI

    Scopus

    3
    被引用数
    (Scopus)
  • Message from the chairs

    Ishikawa, Hiroshi, Okada, Ryuzo, Ukita, Norimichi, Mori, Greg

    Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017    2017年07月  [査読有り]

    DOI

    Scopus

  • Globally and Locally Consistent Image Completion

    Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

    ACM TRANSACTIONS ON GRAPHICS   36 ( 4 )  2017年07月  [査読有り]

     概要を見る

    We present a novel approach for image completion that results in images that are both locally and globally consistent. With a fully-convolutional neural network, we can complete images of arbitrary resolutions by filling in missing regions of any shape. To train this image completion network to be consistent, we use global and local context discriminators that are trained to distinguish real images from completed ones. The global discriminator looks at the entire image to assess if it is coherent as a whole, while the local discriminator looks only at a small area centered at the completed region to ensure the local consistency of the generated patches. The image completion network is then trained to fool the both context discriminator networks, which requires it to generate images that are indistinguishable from real ones with regard to overall consistency as well as in details. We show that our approach can be used to complete a wide variety of scenes. Furthermore, in contrast with the patch-based approaches such as PatchMatch, our approach can generate fragments that do not appear elsewhere in the image, which allows us to naturally complete the images of objects with familiar and highly specific structures, such as faces.

    DOI

    Scopus

    1639
    被引用数
    (Scopus)
  • Guest Editorial: Machine Vision Applications

    Yasuyo Kita, Hiroshi Ishikawa, Takeshi Masuda

    INTERNATIONAL JOURNAL OF COMPUTER VISION   122 ( 2 ) 191 - 192  2017年04月  [査読有り]

    DOI

    Scopus

    4
    被引用数
    (Scopus)
  • Joint Gap Detection and Inpainting of Line Drawings

    Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)     5768 - 5776  2017年  [査読有り]

     概要を見る

    We propose a novel data-driven approach for automatically detecting and completing gaps in line drawings with a Convolutional Neural Network. In the case of existing inpainting approaches for natural images, masks indicating the missing regions are generally required as input. Here, we show that line drawings have enough structures that can be learned by the CNN to allow automatic detection and completion of the gaps without any such input. Thus, our method can find the gaps in line drawings and complete them without user interaction. Furthermore, the completion realistically conserves thickness and curvature of the line segments. All the necessary heuristics for such realistic line completion are learned naturally from a dataset of line drawings, where various patterns of line completion are generated on the fly as training pairs to improve the model generalization. We evaluate our method qualitatively on a diverse set of challenging line drawings and also provide quantitative results with a user study, where it significantly outperforms the state of the art.

    DOI

    Scopus

    34
    被引用数
    (Scopus)
  • Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification

    Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

    ACM TRANSACTIONS ON GRAPHICS   35 ( 4 )  2016年07月  [査読有り]

     概要を見る

    We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features. Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image. The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion. Furthermore, our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors. We validate our approach with a user study and compare against the state of the art, where we show significant improvements. Furthermore, we demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.

    DOI

    Scopus

    630
    被引用数
    (Scopus)
  • Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup

    Edgar Simo-Serra, Satoshi Iizuka, Kazuma Sasaki, Hiroshi Ishikawa

    ACM TRANSACTIONS ON GRAPHICS   35 ( 4 )  2016年07月  [査読有り]

     概要を見る

    In this paper, we present a novel technique to simplify sketch drawings based on learning a series of convolution operators. In contrast to existing approaches that require vector images as input, we allow the more general and challenging input of rough raster sketches such as those obtained from scanning pencil sketches. We convert the rough sketch into a simplified version which is then amendable for vectorization. This is all done in a fully automatic way without user intervention. Our model consists of a fully convolutional neural network which, unlike most existing convolutional neural networks, is able to process images of any dimensions and aspect ratio as input, and outputs a simplified sketch which has the same dimensions as the input image. In order to teach our model to simplify, we present a new dataset of pairs of rough and simplified sketch drawings. By leveraging convolution operators in combination with efficient use of our proposed dataset, we are able to train our sketch simplification model. Our approach naturally overcomes the limitations of existing methods, e. g., vector images as input and long computation time; and we show that meaningful simplifications can be obtained for many different test cases. Finally, we validate our results with a user study in which we greatly outperform similar approaches and establish the state of the art in sketch simplification of raster images.

    DOI

    Scopus

    158
    被引用数
    (Scopus)
  • 地球観測衛星画像上の地物自動認識

    中村, 良介, 石井, 智大, 野里, 博和, 坂無, 英徳, シモセラ, エドガー, 望月, 義彦, 飯塚, 里志, 石川, 博

    人工知能学会全国大会論文集   JSAI2016   {1B24 - 1B24  2016年06月

    DOI

  • Data-Dependent Higher-Order Clique Selection for Artery-Vein Segmentation by Energy Minimization

    Yoshiro Kitamura, Yuanzhong Li, Wataru Ito, Hiroshi Ishikawa

    INTERNATIONAL JOURNAL OF COMPUTER VISION   117 ( 2 ) 142 - 158  2016年04月  [査読有り]

     概要を見る

    We propose a novel segmentation method based on energy minimization of higher-order potentials. We introduce higher-order terms into the energy to incorporate prior knowledge on the shape of the segments. The terms encourage certain sets of pixels to be entirely in one segment or the other. The sets can for instance be smooth curves in order to help delineate pulmonary vessels, which are known to run in almost straight lines. The higher-order terms can be converted to submodular first-order terms by adding auxiliary variables, which can then be globally minimized using graph cuts. We also determine the weight of these terms, or the degree of the aforementioned encouragement, in a principled way by learning from training data with the ground truth. We demonstrate the effectiveness of the method in a real-world application in fully-automatic pulmonary artery-vein segmentation in CT images.

    DOI

    Scopus

    18
    被引用数
    (Scopus)
  • Inference and Learning of Graphical Models: Theory and Applications in Computer Vision and Image Analysis

    Chaohui Wang, Nikos Komodakis, Hiroshi Ishikawa, Olga Veksler, Endre Boros

    COMPUTER VISION AND IMAGE UNDERSTANDING   143   52 - 53  2016年02月  [査読有り]

    DOI

    Scopus

  • Psoas Major Muscle Segmentation Using Higher-Order Shape Prior

    Tsutomu Inoue, Yoshiro Kitamura, Yuanzhong Li, Wataru Ito, Hiroshi Ishikawa

    Medical Computer Vision: Algorithms for Big Data   9601   116 - 124  2016年  [査読有り]

     概要を見る

    We propose a novel segmentation method based on higher-order graph cuts which enables the utilization of prior knowledge regarding anatomical shapes. We applied the method for segmentation of psoas major muscles by using combinations of logistic curves which representing their shapes. The higher-order terms consisting of variables (voxels) just inside or outside of the estimated shapes are added to the energy function to encourage the segmentation results to fit to the shapes. We verified the effectiveness of the method with 20 abdominal CT images. By comparing the segmentation results to the ground truth data prepared by a clinical expert, we validated the method where it achieved the Jaccard similarity coefficient (JSC) of 75.4 % (right major) and 77.5 % (left major). We also confirmed that the proposed method worked well for thick CT images.

    DOI

    Scopus

    5
    被引用数
    (Scopus)
  • Fashion Style in 128 Floats: Joint Ranking and Classification using Weak Data for Feature Extraction

    Edgar Simo-Serra, Hiroshi Ishikawa

    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)     298 - 307  2016年  [査読有り]

     概要を見る

    We propose a novel approach for learning features from weakly-supervised data by joint ranking and classification. In order to exploit data with weak labels, we jointly train a feature extraction network with a ranking loss and a classification network with a cross-entropy loss. We obtain high-quality compact discriminative features with few parameters, learned on relatively small datasets without additional annotations. This enables us to tackle tasks with specialized images not very similar to the more generic ones in existing fully-supervised datasets. We show that the resulting features in combination with a linear classifier surpass the state-of-the-art on the Hipster Wars dataset despite using features only 0.3% of the size. Our proposed features significantly outperform those obtained from networks trained on ImageNet, despite being 32 times smaller (128 single-precision floats), trained on noisy and weakly-labeled data, and using only 1.5% of the number of parameters.

    DOI

    Scopus

    124
    被引用数
    (Scopus)
  • Room Reconstruction from a Single Spherical Image by Higher-order Energy Minimization

    Kosuke Fukano, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Akihiro Sugimoto, Hiroshi Ishikawa

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)     1768 - 1773  2016年  [査読有り]

     概要を見る

    We propose a method for understanding a room from a single spherical image, i.e., reconstructing and identifying structural planes forming the ceiling, the floor, and the walls in a room. A spherical image records the light that falls onto a single viewpoint from all directions and does not require correlating geometrical information from multiple images, which facilitates robust and precise reconstruction of the room structure. In our method, we detect line segments from a given image, and classify them into two groups: segments that form the boundaries of the structural planes and those that do not. We formulate this problem as a higher-order energy minimization problem that combines the various measures of likelihood that one, two, or three line segments are part of the boundary. We minimize the energy with graph cuts to identify segments forming boundaries, from which we estimate structural the planes in 3D. Experimental results on synthetic and real images confirm the effectiveness of the proposed method.

    DOI

    Scopus

    10
    被引用数
    (Scopus)
  • Detection by Classification of Buildings in Multispectral Satellite Imagery

    Tomohiro Ishii, Edgar Simo-Serra, Satoshi Iizuka, Yoshihiko Mochizuki, Akihiro Sugimoto, Hiroshi Ishikawa, Ryosuke Nakamura

    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)     3344 - 3349  2016年  [査読有り]

     概要を見る

    We present an approach for the detection of buildings in multispectral satellite images. Unlike 3-channel RGB images, satellite imagery contains additional channels corresponding to different wavelengths. Approaches that do not use all channels are unable to fully exploit these images for optimal performance. Furthermore, care must be taken due to the large bias in classes, e.g., most of the Earth is covered in water and thus it will be dominant in the images. Our approach consists of training a Convolutional Neural Network (CNN) from scratch to classify multispectral image patches taken by satellites as whether or not they belong to a class of buildings. We then adapt the classification network to detection by converting the fully-connected layers of the network to convolutional layers, which allows the network to process images of any resolution. The dataset bias is compensated by subsampling negatives and tuning the detection threshold for optimal performance. We have constructed a new dataset using images from the Landsat 8 satellite for detecting solar power plants and show our approach is able to significantly outperform the state-of-the-art. Furthermore, we provide an in-depth evaluation of the seven different spectral bands provided by the satellite images and show it is critical to combine them to obtain good results.

    DOI

    Scopus

    36
    被引用数
    (Scopus)
  • 高階エネルギー最小化による1枚の球面画像からの部屋形状推定

    深野 昂祐, 望月 義彦, 石川 博

    情報処理学会研究報告. CVIM, [コンピュータビジョンとイメージメディア]   2015 ( 9 ) 1 - 7  2015年05月

     概要を見る

    本稿では,1 枚の球面画像から単純な部屋の形状を復元する手法を提案する.広い視野を持つ球面画像によって,よりロバストに部屋の構造を認識することができる.部屋の形状は,壁や天井や床といった長方形の面の境界の線分の集合で表される.提案手法では,高階エネルギー最小化によって,検出された線分を境界かそうでない線分に分類する.そして,境界の線分を用いて,壁や天井や床といった部屋を構成する面を推定する.実画像を用いて実験を行い,部屋を構成する面が正しく推定できることを検証した.

    CiNii

  • コンピュータービジョンの数理

    石川 博

    数学   67 ( 2 ) 190 - 202  2015年04月  [査読有り]  [招待有り]

  • Multi-organ Segmentation by Minimization of Higher-order Energy for CT Boundary

    Asuka Okagawa, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa

    2015 14th IAPR International Conference on Machine Vision Applications (MVA)     547 - 550  2015年  [査読有り]

     概要を見る

    In medical image analysis, segmentation of medical images such as Computed Tomography (CT) volumetric images is necessary for further medical image analysis and computer aided intervention. We propose a method for medical image segmentation by higher-order energy minimization. Specifically, we introduce a higher-order term that describes the continuity around the edge points of a CT image. The parameters of the energy terms are determined according to various conditional probabilities learned from sample data with the ground truth. Then we minimize the energy using graph cuts and evaluate the effectiveness of the introduction of the term into the traditional energy.

    DOI

    Scopus

    1
    被引用数
    (Scopus)
  • Multiple-organ Segmentation Based on Spatially-divided Neighboring Data Energy

    Minato Morita, Asuka Okagawa, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa

    2015 14th IAPR International Conference on Machine Vision Applications (MVA)     158 - 161  2015年  [査読有り]

     概要を見る

    Medical image segmentation, e.g., Computed Tomography (CT) volume segmentation, is necessary for further medical image analysis and computer aided intervention. In the standard energy minimization scheme for medical image segmentation, three terms exist in the energy: the data term, the Potts smoothing term, and the probabilistic atlas term. In this paper, we propose a novel potential function that extends the data term. The discriminability of the existing data term, which fully depends on how distinctive the objects of interest appear on CT volume, has problem when some of the objects have similar or same CT values. We overcome this limitation by considering the CT values of a pair of neighboring voxels. Increasing the voxel of interest to be evaluated, the data term become more discriminable even if some objects of interest have similar CT values. We also propose to learn the probability of the neighboring data term for each sub-region, not for each voxel. The proposed neighboring data term can be regarded as to combine the standard data term and the probabilistic atlas.

    DOI

    Scopus

  • Three-DoF Pose Estimation of Asteroids by Appearance-based Linear Regression with Divided Parameter Space

    Naoki Kobayashi, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa

    2015 14th IAPR International Conference on Machine Vision Applications (MVA)     551 - 554  2015年  [査読有り]

     概要を見る

    We present an appearance-based linear regression method for pose estimation from a single image of an asteroid, which can have any pose in the full space of three degree-of-freedom rotation parameters. The method is characterized by its division of the parameter space into multiple regions. Given a large number of training images with known pose parameters, we learn the relationship between the images and the pose parameters, separately for each parameter region, using the standard linear pose estimation. We also create a common subspace such that, when projected to it, the difference between images in the same parameter region tends to collapse. In estimating the pose of an input image, we project it onto the common subspace to determine the parameter region. We apply the method for pose estimation from asteroid images and report the experimental results.

    DOI

    Scopus

    2
    被引用数
    (Scopus)
  • Surface Object Recognition with CNN and SVM in Landsat 8 Images

    Tomohiro Ishii, Ryosuke Nakamura, Hidemoto Nakada, Yoshihiko Mochizuki, Hiroshi Ishikawa

    2015 14th IAPR International Conference on Machine Vision Applications (MVA)     341 - 344  2015年  [査読有り]

     概要を見る

    There is a series of earth observation satellites called Landsat, which send a very large amount of image data every day such that it is hard to analyze manually. Thus an effective application of machine learning techniques to automatically analyze such data is called for. In surface object recognition, which is one of the important applications of such data, the distribution of a specific object on the surface is surveyed. In this paper, we propose and compare two methods for surface object recognition, one using the convolutional neural network (CNN) and the other support vector machine (SVM). In our experiments, CNN showed higher performance than SVM. In addition, we observed that the number of negative samples have a influence on the performance, and it is necessary to select the number of them for practical use.

    DOI

    Scopus

    38
    被引用数
    (Scopus)
  • 高階エネルギー最小化による3次元多臓器セグメンテーション

    石川 博

    インナービジョン   29 ( 11 ) 52 - 52  2014年11月  [招待有り]

  • 1階のデータ項を用いた多臓器同時セグメンテーション

    森田皆人, 岡川明日翔, 小滝将太, 望月義彦, 小山田雄仁, 石川博

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2014 ( 16 ) 1 - 7  2014年05月

     概要を見る

    多臓器の同時セグメンテーションを CRF を用いて行う手法を提案する.従来手法では,隣接画素間の影響を与える項は事前確率のみに基づいていたが,提案手法では,入力画像に依存する条件付確率に基づいた 1 階のデータ項を用いる.真値を伴うデータセットから学習した 1 階のデータ項を用いたセグメンテーション実験の結果を報告する.

    CiNii

  • Convolutional Neural Networkを用いた一般物体認識手法の解析

    石井智大, 望月義彦, 小山田雄仁, 石川博

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2014 ( 14 ) 1 - 8  2014年05月

     概要を見る

    一般物体認識では,近年 Deep Learning を用いた手法が注目されており,その 1 つである Convolutional Neural Network (CNN) は特に優れた結果を示している.しかし,どのような構成の CNN が画像認識に有用であるかは理論的に示されておらず,ノウハウが必要なのが現状である.本研究では CNN を用いた一般物体認識手法において認識精度を変化させる要因の解析を行う.具体的には,Krizhevsky らの手法において,畳込み層のパラメータが認識精度に与える影響を解析するとともに,学習手法の変更が認識精度に与える影響を調べた.

    CiNii

  • 多視点照度差画像を用いた光源方向推定

    岩野俊介, 小山田雄仁, 望月義彦, 石川博

    研究報告コンピュータビジョンとイメージメディア(CVIM)   2014 ( 13 ) 1 - 5  2014年05月

     概要を見る

    画像からの物体・シーンの 3 次元形状の復元において,代表的な手法である多視点ステレオ法と照度差ステレオ法では,物体に対するカメラの位置と光源環境の双方が異なるときには,正確な 3 次元形状を推定することができない.より正確な復元を行うためには,各画像ごとの物体に対する光源方向の推定が必要である.本研究では,多視点照度差画像から 3 次元形状を復元するために必要な光源方向を,入力画像のみを用いて推定する手法を提案し,合成画像を使った予備的な実験の結果を報告する.

    CiNii

  • Coronary Lumen and Plaque Segmentation from CTA Using Higher-Order Shape Prior

    Yoshiro Kitamura, Yuanzhong Li, Wataru Ito, Hiroshi Ishikawa

    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2014, PT I   8673   339 - +  2014年  [査読有り]

     概要を見る

    We propose a novel segmentation method based on multi-label graph cuts utilizing higher-order potentials to impose shape priors. Each higher-order potential is defined with respect to a candidate shape, and takes a low value if and only if most of the voxels inside the shape are foreground and most of those outside are background. We apply this technique to coronary lumen and plaque segmentation in CT angiography, exploiting the prior knowledge that the vessel walls tend to be tubular, whereas calcified plaques are more likely globular. We use the Hessian analysis to detect the candidate shapes and introduce corresponding higher-order terms into the energy. Since each higher-order term has any effect only when its highly specific condition is met, we can add many of them at possible locations and sizes without severe side effects. We show the effectiveness of the method by testing it on the standardized evaluation framework presented at MICCAI segmentation challenge 2012. The method achieved values comparable to the best in each of the sensitivity and positive predictive value, placing it at the top in average rank.

    DOI

    Scopus

    17
    被引用数
    (Scopus)
  • Higher-Order Clique Reduction Without Auxiliary Variables

    Hiroshi Ishikawa

    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)     1362 - 1369  2014年  [査読有り]

     概要を見る

    We introduce a method to reduce most higher-order terms of Markov Random Fields with binary labels into lower-order ones without introducing any new variables, while keeping the minimizer of the energy unchanged. While the method does not reduce all terms, it can be used with existing techniques that transforms arbitrary terms (by introducing auxiliary variables) and improve the speed. The method eliminates a higher-order term in the polynomial representation of the energy by finding the value assignment to the variables involved that cannot be part of a global minimizer and increasing the potential value only when that particular combination occurs by the exact amount that makes the potential of lower order. We also introduce a faster approximation that forego the guarantee of exact equivalence of minimizer in favor of speed. With experiments on the same field of experts dataset used in previous work, we show that the roof-dual algorithm after the reduction labels significantly more variables and the energy converges more rapidly.

    DOI

    Scopus

    17
    被引用数
    (Scopus)
  • A HOG-BASED HAND GESTURE RECOGNITION SYSTEM ON A MOBILE DEVICE

    Lukas Prasuhn, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa

    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)     3973 - 3977  2014年  [査読有り]

     概要を見る

    We propose a HOG-based hand gesture recognition system running on a mobile device. Input data is a video of hand gesture taken by a mobile device. The input data is compared with a database storing hand gesture images, which was synthesized with rotation variation. The comparison is done based on their HOG features and the gesture corresponding to the best-matched image is returned as the result. The recognition algorithm is implemented on a client-server system. The proposed system is applied to American Sign Language (ASL) alphabet recognition problem. The experimental results show that the proposed recognition algorithm improves HOG's robustness under rotation change and compare processing time with different network configurations.

    DOI

    Scopus

    38
    被引用数
    (Scopus)
  • Adaptive higher-order submodular potentials for pulmonary artery-vein segmentation

    Y. Kitamura, Y. Li, W. Ito, H. Ishikawa

    Fifth International Workshop on Pulmonary Image Analysis.    2013年  [査読有り]

  • QPBOアルゴリズムの多値化による非劣モジュラエネルギー最小化

    トーマス ヴィントホイザー, 石川 博, ダニエル クレマース

    画像の認識・理解シンポジウム(MIRU2012)    2012年08月  [査読有り]

  • Generalized Roof Duality for Multi-Label Optimization: Optimal Lower Bounds and Persistency

    Thomas Windheuser, Hiroshi Ishikawa, Daniel Cremers

    COMPUTER VISION - ECCV 2012, PT VI   7577   400 - 413  2012年  [査読有り]

     概要を見る

    We extend the concept of generalized roof duality from pseudo-boolean functions to real-valued functions over multi-label variables. In particular, we prove that an analogue of the persistency property holds for energies of any order with any number of linearly ordered labels. Moreover, we show how the optimal submodular relaxation can be constructed in the first-order case.

    DOI

    Scopus

    11
    被引用数
    (Scopus)
  • Transformation of General Binary MRF Minimization to the First-Order Case

    Hiroshi Ishikawa

    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE   33 ( 6 ) 1234 - 1249  2011年06月  [査読有り]

     概要を見る

    We introduce a transformation of general higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we formalize a framework for approximately minimizing higher-order multilabel MRF energies that combines the new reduction with the fusion-move and QPBO algorithms. While many computer vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models so that higher-order energies can be used to capture the rich statistics of natural scenes. We also show that some minimization methods can be considered special cases of the present framework, as well as comparing the new method experimentally with other such techniques.

    DOI

    Scopus

    101
    被引用数
    (Scopus)
  • グラフカットによるエネルギー最小化法の最新動向

    石川 博

    電子情報通信学会技術研究報告   110 ( 121 ) 45 - 50  2010年07月  [招待有り]

  • 変数フリップによる高階グラフカットの拡張

    石川 博

    画像の認識・理解シンポジウム(MIRU2010)     2076 - 2083  2010年07月  [査読有り]

  • パターンとは何かーー非記号計算と一般対象の情報計量

    石川 博

    情報論的学習理論ワークショップ (IBIS2009)     24 - 45  2009年  [招待有り]

    CiNii

  • 最適化としてのパターン自動発見にむけて

    石川 博

    電子情報通信学会技術研究報告   109 ( 344 ) 49 - 54  2009年

  • Higher-Order Clique Reduction in Binary Graph Cut

    Hiroshi Ishikawa

    CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4     2985 - 2992  2009年  [査読有り]

     概要を見る

    e introduce a new technique that can reduce any higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we combine the reduction with the fusion-move and Q B algorithms to optimize higher-order multi-label problems. hile many vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples, his is because of the lack of efficient algorithms to optimize energies with higher-order interactions. ur algorithm challenges this restriction that limits the representational power of the models, so that higher-order energies can be used to capture the rich statistics of natural scenes. o demonstrate the algorithm, we minimize a third-order energy, which allows clique potentials with up to four pixels, in an image restoration problem. he problem uses the Fields of Experts model, a learned spatial prior of natural images that has been used to test two belief propagation algorithms capable of optimizing higher-order energies. he results show that the algorithm exceeds the B algorithms in both optimization performance and speed.

    DOI

    Scopus

    99
    被引用数
    (Scopus)
  • Higher-Order Gradient Descent by Fusion-Move Graph Cut

    Hiroshi Ishikawa

    2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)     568 - 574  2009年  [査読有り]

     概要を見る

    Markov Random Field is now ubiquitous in many formulations of various vision problems. Recently, optimization of higher-order potentials became practical using higher-order graph cuts: the combination of i) the fusion move algorithm, ii) the reduction of higher-order binary energy minimization to first-order, and iii) the QPBO algorithm. In the fusion move, it is crucial for the success and efficiency of the optimization to provide proposals that fits the energies being optimized. For higher-order energies, it is even more so because they have richer class of null potentials. In this paper, we focus on the efficiency of the higher-order graph cuts and present a simple technique for generating proposal labelings that makes the algorithm much more efficient, which we empirically show using examples in stereo and image denoising.

    DOI

    Scopus

    26
    被引用数
    (Scopus)
  • グラフカット(チュートリアル)

    石川 博

    情報処理学会研究報告   2007-CVIM-158 ( 31 ) 193 - 204  2007年  [招待有り]

  • パターンの疎・再帰的・階層的な表現

    石川 博

    画像の認識・理解シンポジウム(MIRU2007)     726 - 731  2007年

  • Representation and Measure of Structural Information

    H. Ishikawa

    arXiv    2007年

  • Total absolute Gaussian curvature for stereo prior

    Hiroshi Ishikawa

    COMPUTER VISION - ACCV 2007, PT II, PROCEEDINGS   4844   537 - 548  2007年  [査読有り]

     概要を見る

    In spite of the great progress in stereo matching algorithms, the prior models they use, i.e., the assumptions about the probability to see each possible surface, have not changed much in three decades. Here, we introduce a novel prior model motivated by psychophysical experiments. It is based on minimizing the total sum of the absolute value of the Gaussian curvature over the disparity surface. Intuitively, it is similar to rolling and bending a flexible paper to fit to the stereo surface, whereas the conventional prior is more akin to spanning a soap film. Through controlled experiments, we show that the new prior outperforms the conventional models, when compared in the equal setting.

    DOI

    Scopus

    3
    被引用数
    (Scopus)
  • ヒト視覚系から示唆される高階ステレオ事前分布

    石川 博

    画像の認識・理解シンポジウム(MIRU2006)     128 - 134  2006年  [査読有り]

  • Rethinking the prior model for stereo

    H Ishikawa, D Geiger

    COMPUTER VISION - ECCV 2006, PT 3, PROCEEDINGS   3953   526 - 537  2006年  [査読有り]

     概要を見る

    Sometimes called the smoothing assumption, the prior model of a stereo matching algorithm is the algorithm's expectation on the surfaces in the world. Any stereo algorithm makes assumptions about the probability to see each surface that can be represented in its representation system. Although the past decade has seen much continued progress in stereo matching algorithms, the prior models used in them have not changed much in three decades: most algorithms still use a smoothing prior that minimizes some function of the difference of depths between neighboring sites, sometimes allowing for discontinuities.
    However, one system seems to use a very different prior model from all other systems: the human vision system. In this paper, we first report the observations we made in examining human disparity interpolation using stereo pairs with sparse identifiable features. Then we mathematically analyze the implication of using current prior models and explain why the human system seems to use a model that is not only different but in a sense diametrically opposite from all current models. Finally, we propose two candidate models that reflect the behavior of human vision. Although the two models look very different, we show that they are closely related.

    DOI

    Scopus

    18
    被引用数
    (Scopus)
  • Illusory volumes in human stereo perception

    H Ishikawa, D Geiger

    VISION RESEARCH   46 ( 1-2 ) 171 - 178  2006年01月  [査読有り]

     概要を見る

    Any complete theory of human stereopsis must model not only how the correspondences between locations in the two views are determined and the depths are recovered from their disparity, but also how the ambiguity arising from such factors as noise, periodicity, and large regions of constant intensity are resolved and missing data are interpolated. In investigating this process of recovering surface structure from sparse disparity information, using stereo pairs with sparse identifiable features, we made an observation that contradicts all extant models. It suggests the inadequacy of retinotopic representation in modeling surface perception in this stage. We also suggest a possible alternative theory, which is a minimization of the modulus of Gaussian curvature. (c) 2005 Elsevier Ltd. All rights reserved.

    DOI

    Scopus

    5
    被引用数
    (Scopus)
  • Higher-dimensional Segmentation by Minimum-cut Algorithm

    H. Ishikawa, D. Geiger

    IAPR Conference on Machine Vision Applications (MVA2005)     488 - 491  2005年  [査読有り]

  • Finding tree structures by grouping symmetries

    H Ishikawa, D Geiger, R Cole

    TENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1 AND 2, PROCEEDINGS     1132 - 1139  2005年  [査読有り]

     概要を見る

    The representation of objects in images as tree structures is of great interest to vision, as they can represent articulated objects such as people as well as other structured objects like arteries in human bodies, roads, circuit board patterns, etc. Tree structures are often related to the symmetry axis representation of shapes, which captures their local symmetries. Algorithms have been introduced to detect (i) open contours in images in quadratic time (ii) closed contours in images in cubic time, and (iii) tree structures from contours in quadratic time. The algorithms are based on dynamic programming and Single Source Shortest Path algorithms. However, in this paper, we show that the problem of finding tree structures in images in a principled manner is a much harder problem. We argue that the optimization problem of finding tree structures in images is essentially equivalent to a variant of the Steiner Tree problem, which is NP-hard. Nevertheless, an approximate polynomial-time algorithm for this problem exists: we apply a fast implementation of the Goemans-Williamson approximate algorithm to the problem of finding a tree representation after an image is transformed by a local symmetry mapping. Examples of extracting tree structures from images illustrate the idea and applicability of the approximate method.

    DOI

    Scopus

    8
    被引用数
    (Scopus)
  • Exact optimization for Markov random fields with convex priors

    H Ishikawa

    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE   25 ( 10 ) 1333 - 1336  2003年10月  [査読有り]

     概要を見る

    We introduce a method to solve exactly a first order Markov Random Field optimization problem in more generality than was previously possible. The MRF shall have a prior term that is convex in terms of a linearly ordered label set. The method maps the problem into a minimum-cut problem for a directed graph, for which a globally optimal solution can be found in polynomial time. The convexity of the prior function in the energy is shown to be necessary and sufficient for the applicability of the method.

    DOI

    Scopus

    412
    被引用数
    (Scopus)
  • Globally optimal regions and boundaries as minimum ratio weight cycles

    IH Jermyn, H Ishikawa

    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE   23 ( 10 ) 1075 - 1088  2001年10月  [査読有り]

     概要を見る

    We describe anew form of energy functional for the modeling and identification of regions in images. The energy is defined on the space of boundaries in the image domain and can incorporate very general combinations of modeling information both from the boundary (intensity gradients, etc.) and from the interior of the region (texture, homogeneity, etc.). We describe two polynomial-time digraph algorithms for finding the global minima of this energy. One of the algorithms is completely general, minimizing the functional for any choice of modeling information. It runs in a few seconds on a 256x256 image. The other algorithm applies to a subclass of functionals, but has the advantage of being extremely parallelizable. Neither algorithm requires initialization.

    DOI

    Scopus

    133
    被引用数
    (Scopus)
  • Region extraction from multiple images

    H Ishikawa, IH Jermyn

    EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS     509 - 516  2001年  [査読有り]

     概要を見る

    We present a method for region identification in multiple images. A set of regions in different images and the correspondences on their boundaries can be thought of as a boundary in the multi-dimensional space formed by the product of the individual image domains. We minimize an energy functional on the space of such boundaries, thereby identifying simultaneously both the optimal regions in each image and the optimal correspondences on their boundaries. We use a ratio form for the energy functional, thus enabling the global minimization of the energy functional using a polynomial time graph algorithm, among other desirable properties. We choose a simple form for this energy that favours boundaries that lie on high intensity gradients in each image, while encouraging correspondences between boundaries in different images that match intensity values. The latter tendency is weighted by a novel heuristic energy that encourages the boundaries to lie on disparity or optical flow discontinuities, although no dense optical flow or disparity map is computed.

    DOI

  • Multi-scale Feature Selection in Stereo

    H. Ishikawa

    IEEE Computer Society Conference on Computer Vision and Pattern Recognition. (CVPR'99)     1132 - 1137  1999年  [査読有り]

    DOI CiNii

  • Mapping image restoration to a graph problem

    H Ishikawa, D Geiger

    PROCEEDINGS OF THE IEEE-EURASIP WORKSHOP ON NONLINEAR SIGNAL AND IMAGE PROCESSING (NSIP'99)     890 - 894  1999年  [査読有り]

     概要を見る

    We propose a graph optimization method for the restoration of gray-scale images. We consider an arbitrary noise model for each pixel location. We also consider a smooth constraint where the potentials between neighbor pixels are convex functionals. We show how to map this problem to a directed flow graph. Then, a global optimal solution is obtained via the use of the maximum-flow algorithm. The algorithm runs in a polynomial time with respect to the size of the image.

  • Globally Optimal Regions and Boundaries

    I. H. Jermyn, H. Ishikawa

    IEEE International Conference on Computer Vision (ICCV'99)     904 - 910  1999年  [査読有り]

    DOI

  • Occlusions, Discontinuities, and Epipolar Lines in Stereo

    H. Ishikawa, D. Geiger

    European Conference on Computer Vision (ECCV'98)     232 - 248  1998年  [査読有り]

    DOI CiNii

    Scopus

    106
    被引用数
    (Scopus)
  • Segmentation by grouping junctions

    H Ishikawa, D Geiger

    1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS     125 - 131  1998年  [査読有り]

     概要を見る

    We propose a method for segmenting gray-value images. By segmentation, we mean a map from the set of pixels To a small set of levels such that each connected component of the set of pixels with the same level forms a relatively large and "meaningful" region. The method finds a set of levels with associated gray values by first finding junctions in the image and their seeking a minimum set of threshold values that preserves the junctions. Then it finds a segmentation map that maps each pixel to the level with the closest gray value to the pixel data, within a smoothness constraint. For a convex smoothing penalty, we show the global optimal solution for an energy function that fits the data can be obtained in a polynomial time, by a novel use of the maximum-flow algorithm. Our approach is in contrast to a view in computer vision where segmentation is driven by intensity, gradient, usually not yielding closed boundaries.

    DOI

  • 高階グラフカット

    石川 博

    画像の認識・理解シンポジウム(MIRU2009)     7 - 14  [査読有り]

▼全件表示

書籍等出版物

  • "Graph Cuts—Combinatorial Optimization in Vision" (Chapter 2), Olivier Lezoray and Leo Grady ed. "Image Processing and Analysis with Graphs: Theory and Practice"

    Hiroshi Ishikawa( 担当: 共著)

    CRC Press  2012年07月 ISBN: 9781439855072

  • 実践 医用画像解析ハンドブック

    石川 博( 担当: 共著)

    オーム社  2012年

  • "Optimizing Multi-Label MRFs with Convex and Truncated Convex Priors" (Chapter 4), Andrew Blake, Pushmeet Kohli, and Carsten Rother ed. "Markov Random Fields for Vision and Image Processing"

    Hiroshi Ishikawa, Olga Veksler( 担当: 共著)

    MIT Press  2011年09月 ISBN: 9780262015776

  • 「グラフカット」(第2章, pp. 39-74) 斎藤英雄・八木康史(編)「コンピュータビジョン最先端ガイド1: Level Set, Graph Cut, Particle Filter, Tensor, AdaBoost」

    石川 博( 担当: 共著)

    アドコム・メディア  2008年12月 ISBN: 9784915851346

  • “Local Feature Selection and Global Energy Optimization in Stereo,” (Chapter 22, pp. 411-430), Rustam Stolkin ed. "Scene Reconstruction, Pose Estimation and Tracking"

    H. Ishikawa, D. Geiger( 担当: 共著)

    I-Tech Education and Publishing  2007年

講演・口頭発表等

  • The Future of Computer Graphics in the Age of AI and Social Media

    石川 博  [招待有り]

    Computer Graphics International   (カルガリー) 

    発表年月: 2019年06月

  • Higher-Order Random Fields for Image Segmentation

    石川 博  [招待有り]

    Computer Graphics International   (カルガリー) 

    発表年月: 2019年06月

  • Structured Prediction by Fully Convolutional Deep Neural Networks

    石川 博  [招待有り]

    Irish Machine Vision and Image Processing Conference   (ベルファースト)  Irish Pattern Recognition and Classification Society  

    発表年月: 2018年08月

  • Image Completion by CNN with Global and Local Consistency

    石川 博  [招待有り]

    SIAM Conference on Imaging Science   (ボローニャ)  Society for Industrial and Applied Mathematics  

    発表年月: 2018年06月

  • 深層学習による画像変換について

    石川 博  [招待有り]

    第7回バイオメトリクスと認識・認証シンポジウム   (東京) 

    発表年月: 2017年11月

  • 視覚の数理モデルと構造付き予測問題

    石川 博  [招待有り]

    東北大学情報科学研究科 重点プロジェクト第17回講演会 兼 第64回応用数学連携フォーラム   (仙台) 

    発表年月: 2017年10月

  • ⾒えるものは頭で作られる:視覚による空間認識の数理モデル

    石川 博  [招待有り]

    数学連携ワークショップ「数学だからできる現実世界を超えた「メタ」現実の可能性」   (山形) 

    発表年月: 2017年09月

  • Rules and Models versus Data and Machine Learning in Graphics and Vision

    石川 博  [招待有り]

    Computer Graphics International   (横浜) 

    発表年月: 2017年06月

  • Frontiers of Image Processing and Computer Graphics by Deep Learning

    石川 博  [招待有り]

    Computer Graphics International   (横浜) 

    発表年月: 2017年06月

  • ディープラーニングによる画像生成

    石川 博  [招待有り]

    光学シンポジウム   (東京) 

    発表年月: 2017年06月

  • 認識の数理モデルをめざして:分類から構造対象予測へ

    石川 博  [招待有り]

    DENSO A.I. Tech Seminar 「コンピュータビジョンが映し出す、自動運転のセンシング技術の未来」   (東京) 

    発表年月: 2016年10月

  • 深層学習による白黒写真色付けとラフスケッチ線画化

    石川 博  [招待有り]

    ワークショップ「部分空間法・深層学習・大型固有値問題の出会いと融合」   (筑波) 

    発表年月: 2016年09月

  • Automatic Image Colorization and Rough Sketch Cleanup by Deep Learning

    石川 博  [招待有り]

    ACCV2016 Area Chairs Workshop   (基隆) 

    発表年月: 2016年08月

  • MAP Estimation of Markov Random Fields with Some Applications in Medical Imaging

    石川 博  [招待有り]

    Probabilistic Graphical Model Workshop: Sparsity, Structure and High-dimensionality   (立川) 

    発表年月: 2016年03月

  • グラフカット:2次劣モジュラ関数最小化でどこまでやれるか

    石川 博  [招待有り]

    第18回情報論的学習理論ワークショップ   (筑波) 

    発表年月: 2015年11月

  • Higher-Order Graph Cuts and Medical Image Segmentation

    石川 博  [招待有り]

    The workshop on mathematical and computational methods in biomedical imaging and image analysis   (オークランド) 

    発表年月: 2015年11月

  • ビジョンにおけるマルコフ確率場の最大事後確率推定

    石川 博  [招待有り]

    マルコフ確率場モデリングの数理と応用~高次元ビッグデータサイエンスの視点から~   (東京) 

    発表年月: 2015年11月

  • ビジョンにおける離散最適化

    石川 博  [招待有り]

    第27回RAMPシンポジウム   (浜松) 

    発表年月: 2015年10月

  • 最適化としての視覚と認識

    石川 博  [招待有り]

    第6回暗号フロンティアセミナー   (能美) 

    発表年月: 2015年03月

  • Higher-order Graph Cuts

    石川 博  [招待有り]

    ACCV2014 Area Chairs Workshop   (シンガポール) 

    発表年月: 2014年09月

  • グラフカット・その後

    石川 博  [招待有り]

    画像の認識・理解シンポジウム   (東京) 

    発表年月: 2013年07月

  • 高階マルコフ確率場における最大事後確率推定

    石川 博  [招待有り]

    人工知能学会 第87回 人工知能基本問題研究会 (SIG-FPAI)   (横浜) 

    発表年月: 2012年11月

  • Proposal Selection in Higher-order Graph Cuts

    石川 博  [招待有り]

    25th European Conference on Operational Research   (ヴィリニュス) 

    発表年月: 2012年07月

  • ビジョンにおける高階最適化と学習〜ボトムアップアプローチ〜

    石川 博  [招待有り]

    電子情報通信学会PRMU・IBISML、情報処理学会CVIM   (福岡) 

    発表年月: 2010年09月

  • グラフカットによるエネルギー最小化法の最新動向

    石川 博  [招待有り]

    電子情報通信学会医用画像研究会   (徳島) 

    発表年月: 2010年07月

  • パターンとは何か——非記号計算と一般対象の情報計量

    石川 博  [招待有り]

    第12回情報論的学習理論ワークショップ   (福岡) 

    発表年月: 2009年10月

  • A Practical Introduction to Graph Cut

    石川 博  [招待有り]

    The 3rd Pacific-Rim Symposium on Image and Video Technology   (東京) 

    発表年月: 2009年01月

  • パターンとは何か――地に足のついた計算の理論について

    石川 博  [招待有り]

    京都大学数理解析研究所談話会   (京都) 

    発表年月: 2008年11月

  • グラフカットの理論と応用

    石川 博  [招待有り]

    第14回 画像センシングシンポジウム   (横浜) 

    発表年月: 2008年06月

  • Organizing higher-order cliques by sparse representation

    石川 博  [招待有り]

    IPAM Short Program “Graph Cuts and Related Discrete or Continuous Optimization Problems”   (ロサンゼルス) 

    発表年月: 2008年02月

  • Graph algorithms in computer vision

    石川 博  [招待有り]

    Mathematical Aspects of Image Processing and Computer Vision   (札幌) 

    発表年月: 2007年11月

  • グラフカット

    石川 博  [招待有り]

    情報処理学会コンピュータビジョンとイメージメディア研究会   (鹿児島) 

    発表年月: 2007年03月

  • Embedded Graph Algorithms for Computer Vision

    石川 博  [招待有り]

    DIMACS Workshop on Graph Theoretic Methods in Computer Vision   (ニューブランズウィック) 

    発表年月: 1999年05月

▼全件表示

共同研究・競争的資金等の研究課題

  • 画像空間と画像変換学習システムの構造

    研究期間:

    2020年04月
    -
    2025年03月
     

  • 多元計算解剖学における基礎数理

    研究期間:

    2014年06月
    -
    2019年03月
     

     概要を見る

    多くの患者から撮影される様々な種類の医用画像群を利用して人体の総合理解を可能とするモデルを構築する.そのために次の事柄を研究し成果を挙げた:(1) MRIによる新しい撮像原理の開発と既存の撮像法の高精度化法,(2) 画像間の距離の数理基礎と撮影時刻や空間分解能の大きく異なる画像間の位置合わせ法,(3) 形と表面のテクスチャも考慮する臓器領域の写像法,(4)高階グラフカットや深層学習を利用する画像処理法,ならびに(5)情報幾何学による少数データからの統計モデリングの数理基礎.概要の項目(1)の成果により,脳内の電気特性分布を計測出来るようになる.このことにより脳内の腫瘍検出法が増える.また拡散MRIによる画像復元の高速化などが実現する.これらは数理工学的にも医学的にも有意義である.項目(2)により様々な画像群の統合が可能となる.例えば全身MRI画像中の膵癌腫瘍と抽出後の膵癌腫瘍の顕微鏡画像群の位置合わせが可能となった.これは膵癌の基礎研究に寄与するところが大きい.(3)(4)は医用画像より臓器などを抽出し,その結果に基づき臓器モデルを構築する際の精度を改善する.(5)は個人情報保護法などにより多量のデータを利用できないときの統計モデル解析の数理基礎を提供する

  • 高精度形状モデルを基盤とした小惑星地質活動の解析

    日本学術振興会  科学研究費助成事業

    研究期間:

    2013年04月
    -
    2016年03月
     

    平田 成, 出村 裕英, 杉田 精司, 成瀬 継太郎, 太田 直哉, 高橋 成雄, 矢口 勇一, 石川 博, 尾川 順子

     概要を見る

    本研究では,小惑星高精度形状モデル構築手法の確立,小惑星3次元地理情報システムの構築などの技術的目標を達成させる事で,小惑星イトカワのデータ解析の基盤を構築し,イトカワを代表とするrubble-pile小惑星の実態を明らかにすることを目指した.その結果,SPC法とSfM法を組み合わせた迅速かつ高精度の形状モデル構築手法を確立した他,小惑星向け3D-GISの開発に成功した.これらの基盤を活かしつつイトカワ探査データの解析を進め,表面の衝突地形の分布から,数Myr前にイトカワの全球を更新するイベントが起きていた可能性が示唆された.これは,イトカワの回収試料の分析結果とも矛盾しない

  • 構造モデル学習による一般化性能強化

    日本学術振興会  科学研究費助成事業

    研究期間:

    2013年04月
    -
    2015年03月
     

    石川 博

     概要を見る

    CNNにおいては、平行移動で移り合うような神経素子は同じ値になるように訓練し、画像認識においては必須である平行移動による普遍性を持つ特徴をデータから学習させることができる。この平行移動のような一般の変換について同様の効果をめざし、構造の代数的表現と、そのデータ空間におけるセマンティクスを一様に定義することにより、生のデータの中にパターンが存在するかどうかという質問に答えることができる理論の応用を目指した理論的研究を行った。また学習アルゴリズムの応用例として、CNNとsupport vector machine (SVM)によるランドサット衛星画像中の地物認識アルゴリズムを開発した比較した

  • 高階エネルギーの近似最適化と学習

    日本学術振興会  科学研究費助成事業

    研究期間:

    2012年04月
    -
    2015年03月
     

    石川 博

     概要を見る

    劣モジュラでない多値エネルギーを近似的に最小化するアルゴリズムを実現した。高階2値エネルギーを1階エネルギーに還元するアルゴリズムで、既存手法では変数を付加していたが、付加せずに還元することを可能にし、より少ないメモリでより高速な最適化を可能とした。これら高階エネルギー最小化法の応用として、肺の血管のCT画像を動脈と静脈に分けるセグメンテーションに高階エネルギーを使い、肺血管の形状をエネルギー中に表現することを可能にした。また、心臓の冠動脈中に生じるプラークと血管壁を区別したセグメンテーションを、血管内腔、プラーク、血管壁の3ラベルのラベル付け問題と考え高階エネルギーを使って高精度化した

  • 高階エネルギー最小化による3次元多臓器セグメンテーション

    科学研究費助成事業(早稲田大学)  科学研究費助成事業(新学術領域研究(研究領域提案型))

    研究期間:

    2012年
    -
    2013年
     

     概要を見る

    多臓器セグメンテーションのために高階エネルギーを最小化する新たなアルゴリズムを開発した。これは、従来手法と異なり、付加変数を必要としない。この成果はCVPR2014に採択された。また、セグメンテーション結果の評価により最適なセグメンテーション結果を選択する方法を検討した。各セグメンテーション結果に対して,トレーニングデータから得られる統計から尤度を計算することで,セグメンテーション結果の評価を行った。セグメンテーション結果の良さは,セグメンテーション結果と正解データとの一致率の高さと定義し,尤度と一致率の相関を調べた。また他にも、肺の血管のCT画像を動脈と静脈に分けるセグメンテーションに高階エネルギー最小化を応用した。これはワークショップPIA2013で発表した。一方、心臓の動脈硬化の程度をCT画像から測定するためのアルゴリズムを開発し、国際会議MICCAI2014に採択された。

  • 非記号計算の基礎理論の構築と構造学習への応用

    戦略的創造研究推進事業  戦略的創造研究推進事業(さきがけ)

    研究期間:

    2009年
    -
    2013年
     

     概要を見る

    昨今増加が著しい画像や映像、各種計測データ等のアナログ情報で表される現実の世界と、インターネットに代表され、デジタル記述されるサイバー世界における情報の概念の間に橋渡しをすることを目指します。そのために構造一般を記述する基本である計算の概念を非記号空間内に直接表現し、複雑な構造を持つ情報一般を統一的に扱う理論を構築します。また画像などの高次元データ中にパターンを見つけることへの応用を目指します。

  • 構造情報表現によるパターン発見の研究

    科学研究費助成事業(名古屋市立大学)  科学研究費助成事業(萌芽研究)

    研究期間:

    2007年
    -
    2009年
     

     概要を見る

    情報科学では、抽象化された情報と現実の世界の一般対象の関係、すなわち符号化は、任意であるとされる。逆に、一般対象に内包される情報の概念は、符号化できる対象の全体を限定して、その範囲でのみ意味を持つ。しかし、対象の全体が大きくなると、その全体に共通して適用可能な情報概念の定義が難しくなる。ビットで表わされる記号の世界を離れて情報について考えると、他にも符号化の任意性の喪失や、一般対象の規則性と符号の規則性の不一致等の問題が生ずる。本研究では、「図式とその断面によるパターン表現」という新概念を定式化し、統一的で一般性が高く、パターンの構造情報と実装依存部分を分離できる非記号情報の表現方法を提案した。これはそのパターンの含まれる空間を特徴付ける写像の集合に対して相対的に定義されるが、自然数を特徴付ける写像(0を与える写像と後者写像)に相対的に定義されたとき、この表現により表現可能な写像全体は帰納的部分関数全体と一致することを示した。また、この表現によるパターン発見を目指して、最適化問題との関係を探るうち、高次元データの中に高階相関構造を見つけることの重要性を認識し、コンピュータビジョンにおける新しい曲面事前モデルの定式化についても検討した。これから示唆された曲面事前モデルであるガウス曲率絶対値最小化を、より性能の高い最新の最適化技術で行うため、グラフカットにおける高階エネルギーの最小化について研究した結果、任意の高階2値エネルギーを1階に変換する方法を発見し、またそれを繰り返し使うことによる多値エネルギー最小化法も開発した

▼全件表示

 

現在担当している科目

▼全件表示

 

他学部・他研究科等兼任情報

  • 理工学術院   大学院基幹理工学研究科

学内研究所・附属機関兼任歴

  • 2022年
    -
    2024年

    理工学術院総合研究所   兼任研究員