TABLE OF CONTENTS |
Tuesday, May 19, 2015 |
Session 1: Recognition |
| 1-1 | Biased Discriminant Analysis with Feature Line Embedding for Interactive Image Retrieval | 1 |
| Yu-Chen Wang, Chin-Chuan Han, Chang-Hsing Lee, Kuo-Chin Fan, Taiwan |  |
| 1-2 | Discriminative Learning of Apparel Features | 5 |
| Rasmus Rothe, Marko Ristin, Matthias Dantone, Luc Van Gool, Switzerland | |
| 1-3 | Multi-View Hypotheses Transfer for Enhanced Object Recognition in Clutter | 10 |
| Thomas Faulhammer, Michael Zillich, Markus Vincze, Austria | |
| 1-4 | Affine Invariant Visual Phrases for Object Instance Recognition | 14 |
| Viorica Pătrăucean, Maks Ovsjanikov, United Kingdom | |
Session 2: 3D |
| 2-1 | Entire Shape Scan System with Multiple Pro-Cams Using Texture Information and Accurate Silhouette Creating Technique | 18 |
| Yoshinori Oki, Marco Visentini-Scarzanella, Tomohiro Wada, Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki, Japan |  |
| 2-2 | Automatic 3D Industrial Point Cloud Modeling and Recognition | 22 |
| Guan Pang, Rongqi Qiu, Jing Huang, Suya You, Ulrich Neumann, United States of America | |
| 2-3 | Enhanced Surface Normal Computation by Exploiting RGB-D Sensory Information | 26 |
| Jens Hedrich, Francois Genois, Dietrich Paulus, Marcin Grzegorzek, Germany | |
Session 3: IAPR Invited Talks 1 |
| 3-1 | 3D Reconstruction from Photographs – Principles and Applications | 30 |
| Jan Heller *1, Michal Havlena *2, Michal Jancosek *3, Akihiko Torii *4, Tomas Pajdla *1
(1: CTU in Prague, 2: ETH Zurich, 3: Capturing Reality, 4: Tokyo Institute of Technology)
| |
Session 5: Poster Session 1 |
| 5-2 | Discussion on a Method to Extract Scallop Using Line Convergence Index Filter from Granule-Sand Seabed Videos | 35 |
| Koichiro Enomoto, Masashi Toda, Yasuhiro Kuwahara, Japan | |
| 5-3 | Structural Inpainting of Road Patches for Anomaly Detection | 41 |
| Asim Munawar, Clement Creusot, Japan | |
| 5-4 | Semantic Rich ICM Algorithm for VHR Satellite Images Segmentation | 45 |
| Jérémie Sublime, Andrés Troya-Galvis, Younès Bennani, Antoine Cornuéjols,
Pierre Gançarski, France |
|
| 5-5 | Using Polynomials to Correct Non-Uniform Backgrounds in Thermal Images Caused by Uneven Heating | 49 |
| Kai-Yi Zheng, Yu-Sung Chang, Kai-Hong Wang, Yuan Yao, Taiwan | |
| 5-6 | An Innovative of Pyramid-Based Fusion for Generating the HDR Images in Common Display Devices | 53 |
| Suthum Keerativittayanun, Toshiaki Kondo, Kazunori Kotani, Teera Phatrapornnant, Thailand |
|
| 5-7 | Inferior Alveolar Canal Segmentation in Cone Beam Computed Tomography Images Using an Adaptive Diffusion Flow Active Contour Model | 57 |
| Chadaporn Keatmanee, Stanislav Makhanov, Saowapak Thongvigitmanee, Kazunori Kotani, Toshiaki Kondo, Thailand | |
| 5-8 | 3D Lung Nodule Candidates Detection in Multiple Scales | 61 |
| Jorge Novo, Luis Gonçalves, Ana Maria Mendonça, Aurélio Campilho, Portugal | |
| 5-9 | Modeling the Stone Floor Based on Excavation Information Using Implicit Polynomial | 65 |
| Yoshihiro Sato, Yosuke Shinya, Bo Zheng, Takeshi Oishi, Katsushi Ikeuchi, Japan | |
| 5-10 | Hierarchical Summarization for Easy Video Applications | 69 |
| Nithya Sudhakar, Sharat Chandran, India | |
| 5-11 | Character Extraction by Integrating Color into Edge-Based Methods | 73 |
| Naoki Chiba, Xinhao Liu, Japan | |
| 5-12 | Face Photo-Sketch Recognition Based on Joint Dictionary Learning | 77 |
| Jixuan Liu, Seho Bae, Hanjae Park, Lei Li, Seongbeak Yoon, Juneho Yi, Korea, South | |
| 5-13 | A Hybrid Approach to Pedestrian Clothing Color Attribute Extraction | 81 |
| Mu Gao, Yuning Du, Haizhou Ai, Shihong Lao, China | |
| 5-14 | Scene Retrieval by Unsupervised Salient Part Discovery | 85 |
| Naotoshi Sugegaya, Kanji Tanaka, Kentaro Yanagihara, Japan | |
| 5-16 | An Efficient FPGA Implementation of the Harris Corner Feature Detector | 89 |
| Tak Lon Chao, Kin Hong Wong, China |
|
| 5-17 | Mobile Real-Time Single Image 3D Corridor Reconstruction Using J-Linkage | 94 |
| Greg Olmschenk, Zhigang Zhu, United States of America | |
| 5-18 | Egocentric Articulated Pose Tracking for Action Recognition | 98 |
| Haruka Yonemoto, Kazuhiko Murasaki, Tatsuya Osawa, Kyoko Sudo, Jun Shimamura, Yukinobu Taniguchi, Japan | |
| 5-19 | A Novel Spiral Addressing Scheme for Rectangular Images | 102 |
| Min Jing, Bryan Scotney, Sonya Coleman, Martin McGinnity, United Kingdom | |
| 5-20 | Illuminant Classification Based on Random Forest | 106 |
| Bozhi Liu, Guoping Qiu, United Kingdom | |
| 5-21 | Transfer Learning Method Using Multi-Prediction Deep Boltzmann Machines for a Small Scale Dataset | 110 |
| Yoshihide Sawada, Kazuki Kozuka, Japan | |
| 5-22 | Part-Segment Features for Articulated Pose Estimation | 114 |
| Norimichi Ukita, Japan | |
| 5-23 | Connectivity-Based Error Evaluation for Ellipse Fitting | 118 |
| Tomonari Masuzaki, Yasuyuki Sugaya, Japan | |
| 5-24 | Weighted Hough Forest for Object Detection | 122 |
| Yusuke Murai, Yuji Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi, Japan | |
| 5-25 | Fine-Grained Classification of Identity Document Types with Only One Example | 126 |
| Marcel Simon, Erik Rodner, Joachim Denzler, Germany | |
| 5-26 | Similar Handwritten Chinese Character Recognition Based on Adaptive Discriminative Locality Alignment | 130 |
| Xiwen Qu, Ning Xu, Weiqiang Wang, Ke Lu, China | |
| 5-27 | Pose Estimation of Textureless Objects in Cluttered Environments | 134 |
| Blaž Bratanič, Boštjan Likar, Franjo Pernuš, Dejan Tomaževič , Slovenia | |
| 5-28 | Grouped Outlier Removal for Robust Ellipse Fitting | 138 |
| Mang Shao, Yoshihisa Ijiri, Kosuke Hattori, United Kingdom |
|
| 5-29 | Reliable Background Prediction Using Approximated GMM | 142 |
| Tomosuke Maeda, Tomohiko Ohtsuka, Japan | |
| 5-30 | Manufactured Object Sub-Segmentation Based on Reflection Motion Estimation | 146 |
| Qinglin Lu, Olivier Laligant, Eric Fauvet, Anastasia Zakharova, France | |
| 5-31 | Unsupervised Muscle Region Extraction by Fuzzy Decision Based Saliency Feature Integration on Thigh MRI for 3D Modeling | 150 |
| Nevrez Imamoglu, Jose Gomez-Tames, Siyu He, Dong-Yun Gu, Kahori Kita, Wenwei Yu, Japan | |
| 5-32 | Training-Free Moving Object Detection System Based on Hierarchical Color-Guided Motion Segmentation | 154 |
| Xinfeng Bao, Gijs Dubbelman, Svitlana Zinger, Peter H. N. de With, Netherlands | |
| 5-33 | Multiple-Organ Segmentation Based on Spatially-Divided Neighboring Data Energy | 158 |
| Minato Morita, Asuka Okagawa, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan | |
| 5-34 | WM-SBA: Weighted Multibody Sparse Bundle Adjustment | 162 |
| Kai Cordes, Mark Hockner, Hanno Ackermann, Bodo Rosenhahn, Jörn Ostermann, Germany | |
| 5-35 | Bundle Adjustment Revisited for Slam with RGB-D Sensors | 166 |
| Kathia Melbouci, Sylvie Naudet Collette, Vincent Gay-Bellile, Omar Ait Aider, Mathieu Carrier, Michel Dhome, France | |
| 5-36 | Tracking a Table Tennis Ball for Umpiring Purposes | 170 |
| Hnin Myint, Patrick Wong, Laurence Dooley, Adrian Hopgood, United Kingdom | |
| 5-37 | A New Method to Detect Nystagmus for Vertigo Diagnosis System by Eye Movement Velocity | 174 |
| Theekapun Charoenpong, Visan Mahasitthiwat, Preeyanan Pattrapisetwong, Thailand | |
| 5-39 | A Lens Collar Auto-Inspection System | 182 |
| Chien-Chih Wang, Ssu-Han Chen, Taiwan | |
| 5-40 | Surface Defect Detection in Low-Contrast Images Using Basis Image Representation | 186 |
| Du-Ming Tsai, Yan-Hsin Tseng, Wei-Yao Chiu, Taiwan | |
Wednesday, May 20, 2015 |
Session 6: ITS |
| 6-1 | Augmenting Off-the-Shelf Paper Maps Using Intersection Detection and Geographical Information Systems | 190 |
| Liming Yang, Jean-Marie Normand, Guillaume Moreau, France |
|
| 6-2 | Leveraging Image Based Prior for Visual Place Recognition | 194 |
| Taisho Tsukamoto, Kanji Tanaka, Japan | |
| 6-3 | Beyond Thinking in Common Categories: Predicting Obstacle Vulnerability Using Large Random Codebooks | 198 |
| Johannes Ruhle, Erik Rodner, Joachim Denzler, Germany | |
| 6-4 | Road Sign-Aided Estimation of Visibility Conditions | 202 |
| Rachid Belaroussi, Dominique Gruyer, France | |
Session 7: Industry |
| 7-1 | Automated Visual Inspection of Pharmaceutical Tablets in Heavily Cluttered Dynamic Environments | 206 |
| Gregor Podrekar, Blaž Bratanič, Boštjan Likar, Franjo Pernuš, Dejan Tomaževič, Slovenia | |
| 7-2 | Visual Words for Automated Visual Inspection of Bulk Materials | 210 |
| Matthias Richter, Tomas Längle, Jürgen Beyerer, Germany | |
| 7-3 | OLED Panel Defect Detection Using Local Inlier-Outlier Ratios and Modified LBP | 214 |
| Vishwanath Sindagi, Sumit Srivastava, India | |
| 7-4 | Pixel-Wise Radiometric Line Scanner Calibration | 218 |
| Francois Johannes Louw, Masaaki Iiyama, Takuya Funatomi, Michihiko Minoh, Japan | |
Session 8: IAPR Invited Talk 2 |
| 8-1 | Color Image Processing from the Physical, Psychological and Biological Viewpoints | 222 |
| Prof. Johji Tajima (Nagoya City University) |
|
Session 9: Pedestrian |
| 9-1 | Boosted Pedestrian Detector Adaptation in Specific Scenes | 230 |
| Puhao Ma, Lei Sun, Haizhou Ai, Shun Sakai, China | |
| 9-2 | Fast Discrimination by Early Judgment Using Linear Classifier | 234 |
| Takato Kurokawa, Yuji Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi, Japan | |
Session 10: Poster Session2 |
| 10-1 | Automatic Grape Bunch Detection in Vineyards for Precise Yield Estimation | 238 |
| Scarlett Liu, Mark Albert Whitty, Stephen Cossell, Australia | |
| 10-2 | OKIRAKU Search: Leaf Images Based Visual Tree Search System | 242 |
| Takeshi Saitoh, Toshihiro Iwata, Kentaro Wakisaka, Japan | |
| 10-3 | Pedestrian Detection in Thermal Images Using Adaptive Fuzzy C-Means Clustering and Convolutional Neural Networks | 246 |
| Vijay John, Zheng Liu, Seiichi Mita, Bin Qi, Japan | |
| 10-4 | PerSEE: a Central Sensors Fusion Electronic Control Unit for the Development of Perception-Based ADAS | 250 |
| Dominique Gruyer, Rachid Belaroussi, Xuanpeng Li, Benoit Lusetti, Marc Revilloud, Sebastien Glaser, France | |
| 10-5 | Metamerism-Based Shading Illusion | 255 |
| Daisuke Miyazaki, Takafumi Saneshige, Masashi Baba, Ryo Furukawa, Masahito Aoyama, Shinsaku Hiura, Japan | |
| 10-6 | Digital Image Watermarking on Illumination Component | 259 |
| Piyanart Chotikawanid, Kharittha Thongkor, Pipat Supasirisun, Thumrongrat Amornraksa, Thailand | |
| 10-8 | Temporal-Spatial Validation of Knot-Tying Procedures Using RGB-D Sensor for Training of Surgical Operation | 263 |
| Yoko Ogawa, Nobutaka Shimada, Yoshiaki Shirai, Yoshimasa Kurumi, Masaru Komori, Japan |
|
| 10-9 | Document Image Dataset Indexing and Compression Using Connected Components Clustering | 267 |
| Houssem Chatbri, Keisuke Kameyama, Japan | |
| 10-10 | Development of Design and Operation Supporting Techniques for Product Inspection Devices Using Virtual Devices | 271 |
| Fumiyuki Takahashi, Hideki Abe, Susumu Haga, Tetsuo Koezuka, Japan | |
| 10-11 | A Hybrid Wavelet and Temporal Fusion Algorithm for Film and Video Denoising | 275 |
| Hannes Fassold, Peter Schallauer, Austria | |
| 10-12 | A Deep-Learning Approach to Facial Expression Recognition with Candid Images | 279 |
| Wei Li, Min Li, Zhong Su, Zhigang Zhu, United States of America | |
| 10-13 | Multi-Genomic Curve Extraction | 283 |
| Raphaël Labayrade, Mathias Ngo, France | |
| 10-14 | Bag of Words Representation and SVM Classifier for Timber Knots Detection on Color Images | 287 |
| Mohamad Mazen Hittawe, Désiré Sidibé, Fabrice Mériaudeau, France | |
| 10-15 | Non-Parametric Image Transforms for Sparse Disparity Maps | 291 |
| Dexmont Peña, Alistair Sutherland, Ireland | |
| 10-16 | Increasing the Precision of Junction Shaped Features | 295 |
| Kai Cordes, Jörn Ostermann, Germany | |
| 10-17 | On the Number of Holes of a 2-D Binary Object | 299 |
| Humberto Sossa, Mexico | |
| 10-18 | Local Behavior Modeling Based on Long-Term Tracking Data | 303 |
| Rainer Planinc, Martin Kampel, Austria | |
| 10-19 | A Practical Classifier for Photographs and Non-Photographic Images Based on Local Visual Features | 307 |
| Kei Terayama, Hirohisa Hioki, Japan | |
| 10-20 | Automatic Target Recognition by Infrared and Visible Image Matching | 312 |
| Kai-Sheng Cheng, Huei-Yung Lin, Taiwan |
|
| 10-21 | Sparse Image Reconstruction by Two Phase RBM Learning: Application to Mine Planning | 316 |
| Yanyan Mu, Frank Ferrie, Roussos Dimitrakopoulos, Canada |
|
| 10-22 | Occlusion-Free Appearance Modeling of Body Parts for Human Pose Estimation | 321 |
| Yuki Kawana, Norimichi Ukita, Norihiro Hagita, Japan | |
| 10-23 | Semantic Mapping for Mobile Outdoor Robots | 325 |
| Dagmar Lang, Susanne Friedmann, Jens Hedrich, Dietrich Paulus, Germany | |
| 10-25 | Action Recognition in Bed Using BAMs for Assisted Living and Elderly Care | 329 |
| Manuel Martinez, Lukas Rybok, Rainer Stiefelhagen, Germany | |
| 10-26 | Geometric Interpretation of Fisher's Linear Discriminant Analysis through Communication Theory | 333 |
| Jun Fujiki, Masaru Tanaka, Hitoshi Sakano, Akisato Kimura, Japan | |
| 10-27 | Correspondence Rejection by Trilateration for 3D Point Cloud Registration | 337 |
| Kishan Lachhani, Jifang Duan, Hadi Baghsiahi, Eero Willman, David R. Selviah, United Kingdom | |
| 10-28 | Surface Object Recognition with CNN and SVM in Landsat 8 Images | 341 |
| Tomohiro Ishii, Ryosuke Nakamura, Hidemoto Nakada, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan | |
| 10-29 | Lane Detection in Surveillance Videos Using Vector-Based Hierarchy Clustering and Density Verification | 345 |
| Shan-Yun Teng, Kun-Ta Chuang Chuang, Chun-Rong Huang, Cheng-Chun Li, Taiwan | |
| 10-30 | Circle-Based Eye Center Localization (CECL) | 349 |
| Yustinus Eko Soelistio, Eric Postma, Alfons Maes, Indonesia | |
| 10-31 | Unsupervised Figure-Ground Segmentation Using Edge Detection and Game-Theoretical Graph-Cut Approach | 353 |
| Yu-Min Hsiao, Long-Wen Chang, Taiwan | |
| 10-32 | Visually Salient Features for Highway Scene Analysis | 357 |
| Anurag Singh, Chee Hung Henry Chu, Michael A. Pratt, United States of America | |
| 10-34 | General-Purpose Road Boundary Detection with Stereo Camera | 361 |
| Takuya Nanri, Abdelaziz Khiat, Hiroyuki Furusho, Japan | |
| 10-35 | Tracking Image Features with PCA-SURF Descriptors | 365 |
| Ardhisha Pancham, Daniel Withey, Glen Bright, South Africa | |
| 10-36 | A Novel Multi Modal Tracking Method Based on Depth and Semantic Color Features for Human Robot Interaction | 369 |
| Aswin Chandarr, Maja Rudinac, Pieter Jonker, Netherlands | |
| 10-37 | Distributed Sigma Point Information Filters for Target Tracking in Camera Networks | 373 |
| Shiva Kumar K A, K. R. Ramakrishnan, G. N. Rathna, India |
|
| 10-38 | A Dataset for Computer-Vision-Based PCB Analysis | 378 |
| Christopher Pramerdorfer, Martin Kampel, Austria | |
Thursday, May 21, 2015 |
Session 11: Action |
| 11-1 | Effective Fusing the Factored Matrices in Dual Tensors for Action Recognition | 386 |
| Chung-Yang Hsieh, Wei-Yang Lin, Taiwan | |
| 11-2 | Human Motion Prediction Considering Environmental Context | 390 |
| Igi Ardiyanto, Jun Miura, Japan | |
| 11-3 | Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking | 394 |
| Edgar Simo-Serra, Carme Torras, Francesc Moreno-Noguer, Spain | |
| 11-4 | Human Arm Pose Modeling with Learned Features | 398 |
| Chongguo Li, Nelson H.C. Yung, Edmund Lam, China | |
Session 12: Biomedical |
| 12-1 | Dorsal Hand Vein Recognition Based on EP-Tree | 402 |
| Jen-Chun Lee, Taiwan | |
| 12-2 | Compressive Sensing Reconstruction Using Collaborative Sparsity among Color Channels | 406 |
| Satoshi Satou, Motonori Ishii, Yoshihisa Kato, Kunio Nobori, Takeo Azuma, Japan | |
| 12-3 | Dependence on the Display Methods of Change in Accommodation and Convergence When a Target Moves along the Depth Direction | 410 |
| Yuki Yokoyama, Shinya Mochiduki, Hideaki Takahira, Mitsuho Yamada, Japan | |
| 12-4 | Non-Contact Pulse Transit Time Measurement Using Imaging Camera, and Its Relation to Blood Pressure | 414 |
| Kenta Murakami, Mototaka Yoshioka, Jun Ozawa, Japan | |
Session 13: IAPR Invited Talk 3 |
| 13-1 | Research Opportunities in Creating Medical Images | 418 |
| | |
Session 14: Poster Session 3 |
| 14-1 | Mobile 3D Wood Pile Surveying | 422 |
| Christopher Herbon, Benjamin Otte, Klaus-Dietz Tönnies, Bernd Stock, Germany | |
| 14-2 | Portable, Automatic Water Level Estimation Using Mobile Phone Cameras | 426 |
| Machiel Bruinink, Aswin Chandarr, Maja Rudinac, Peter-Jules van Overloop, Pieter Jonker, Netherlands | |
| 14-3 | Annotation Driven MAP Search Space Estimation for Sliding-Window Based Person Detection | 430 |
| Stefan Becker, Wolfgang Hubner, Michael Arens, Germany | |
| 14-4 | Tsai Camera Calibration Enhanced | 435 |
| Trevor Gee, Patrice Delmas, Nick Stones-Havas, Chris Sinclair, Wannes Van Der Mark, Wei Li, Heide Friedrich, Georgy Gimel'farb, New Zealand | |
| 14-5 | Combined Generation of Road Marking and Road Sign Databases Applied to Consistency Checking of Pedestrian Crossings | 439 |
| Lykele Hazelhoff, Ivo Creusen, Thomas Woudsma, Xinfeng Bao, Peter H. N. de With, Netherlands | |
| 14-6 | Fast Single Image Dehazing through Edge-Guided Interpolated Filter | 443 |
| Ximei Zhu, Ying Li, Yu Qiao, China | |
| 14-7 | Discriminating Motion Patterns of ACL Reconstructed Patients from Healthy Individuals | 447 |
| Worapan Kusakunniran, Nattaporn Dirakbussarakom, Nantawat Prachasri, Duangkamol Yangchaem, Jos Vanrenterghem, Mark Robinson, Thailand | |
| 14-8 | Computer Vision-Based Approach for Rite Decryption in Old Societies | 451 |
| Jilliam María Díaz Barros, Cédric Demonceaux, Adlane Habed, Alamin Mansouri, France | |
| 14-9 | The Method Based on View-Directional Consistency Constraints for Robust 3D Object Recognition | 455 |
| Jun Shimamura, Taiga Yoshida, Yukinobu Taniguchi, Hiroko Yabushita, Kyoko Sudo, Kazuhiko Murasaki, Japan | |
| 14-10 | Efficient Three Dimensional Rotation Estimation for Camera-Based OCR | 459 |
| Kanta Kuramoto, Wataru Ohyama, Tetsushi Wakabayashi, Fumitaka Kimura, Japan | |
| 14-11 | Intelligent Autofocus with Adaptive Depth of Field | 463 |
| Pu-Chuan Kang, Huei-Yung Lin, Taiwan | |
| 14-13 | Spatio-Temporal Texture-Based Feature Extraction for Spontaneous Facial Expression Recognition | 467 |
| Siti Khairuni Amalina Kamarol, Nor Syazana Meli, Mohamed Hisham Jaward, Nader Kamrani, Malaysia | |
| 14-14 | Spatio-Temporal Descriptor for Abnormal Human Activity Detection | 471 |
| Boon Lung Fam, Mohamed Hisham Jaward, Jussi Parkkinen, Malaysia | |
| 14-15 | Expanding Histogram of Colors with Gridding to Improve Tracking Accuracy | 475 |
| Kourosh Meshgi, Shin Ishii, Japan | |
| 14-16 | Measuring the Complexity of Two Dimensional Binary Patterns ?Sub-Symmetries Versus Papentin Complexity? | 480 |
| Godfried T. Toussaint, Noris S. Onea, Quan H. Vuong, United Arab Emirates | |
| 14-17 | Novel Spatio-Temporal Features for Fingertip Writing Recognition in Egocentric Viewpoint | 484 |
| Muhammad Zaid Hameed, Guillermo Garcia-Hernando, Tae-Kyun Kim, United Kingdom | |
| 14-18 | 3D Hand Skeleton Model Estimation from a Depth Image | 489 |
| Chin-Yun Fan, Meng-Hsuan Lin, Te-Feng Su, Shang-Hong Lai, Chih-Hsiang Yu, Taiwan | |
| 14-19 | Digital Image Watermarking Based on Regularized Filter | 493 |
| Kharittha Thongkor, Pipat Supasirisun, Thumrongrat Amornraksa, Thailand | |
| 14-20 | Knot Detection in X-Ray Images of Wood Planks Using Dictionary Learning | 497 |
| Mattias Hansson, Alexandru Enescu, Sami S. Brandt, Denmark | |
| 14-21 | A Discriminative Cascade CNN Model for Offline Handwritten Digit Recognition | 501 |
| Shulan Pan, Yanwei Wang, Changsong Liu, Xiaoqing Ding, China | |
| 14-22 | Visual Detection and Species Classification of Orchid Flowers | 505 |
| Steven Puttemans, Toon Goedemé, Belgium | |
| 14-23 | Probabilistic Nodes for Modelling Classification Uncertainty for Random Forest | 510 |
| Florian Baumann, Karsten Vogt, Arne Ehlers, Bodo Rosenhahn, Germany | |
| 14-24 | METU Dataset: A Big Dataset for Benchmarking Trademark Retrieval | 514 |
| Osman Tursun, Sinan Kalkan, Turkey | |
| 14-25 | Image Annotation Via Deep Neural Network | 518 |
| Chengjian Sun, Songhao Zhu, Zhe Shi, China | |
| 14-26 | A Study on the Robustness of Shape Descriptors to Common Scanning Artifacts | 522 |
| Ferran Roure, Yago Díez, Xavier Lladó, Josep Forest, Tomislav Pribanic, Joaquim Salvi, Spain | |
| 14-27 | A Closed-form Estimate of 3D ICP Covariance | 526 |
| Prakhya Sai Manoj, Bingbing Liu, Yan Rui, Weisi Lin, Singapore | |
| 14-28 | View Extension for Teleoperated MAV | 530 |
| Ren Foo Lim, Akihiko Torii, Masatoshi Okutomi, Japan | |
| 14-29 | Object Detection in Surveillance Video from Dense Trajectories | 535 |
| Mengyao Zhai, Lei Chen, Mehran Khodabandeh, Jinling Li, Greg Mori, Canada | |
| 14-30 | A Deep Reinforcement Learning Approach to Character Segmentation of License Plate Images | 539 |
| Farnaz Abtahi, Zhigang Zhu, Aaron M. Burry, United States of America | |
| 14-31 | VHR Satellite Image Segmentation Based on Topological Unsupervised Learning | 543 |
| Nistor Grozavu, Nicoleta Rogovschi, Guénaël Cabanes, Andrés Troya-Galvis,
Pierre Gançarski, France | |
| 14-32 | Multi-Organ Segmentation by Minimization of Higher-Order Energy for CT Boundary | 547 |
| Asuka Okagawa, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan | |
| 14-33 | Three-DoF Pose Estimation of Asteroids by Appearance-Based Linear Regression with Divided Parameter Space | 551 |
| Naoki Kobayashi, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan | |
| 14-34 | Embedded Human-Following Mobile-Robot with an RGB-D Camera | 555 |
| Minh-Quoc Do, Chang-Hong Lin, Taiwan |
|
| 14-35 | Respiratory Motion Prediction from CBCT Image Observations Using UKF | 559 |
| Manivannan Sundarapandian, Ramakrishnan Kalpathi, R Alfredo Siochi, India | |
| 14-36 | A Portable 6-DOF Motion Tracker Using High-Accuracy AR Markers ?? First Report on the Feasibility | 563 |
| Hideyuki Tanaka, Yasushi Sumi, Yoshio Matsumoto, Japan | |
| 14-37 | Towards 3D Human Posture Estimation Using Multiple Kinects Despite Self-Contacts | 567 |
| Andrew Phan, Frank P. Ferrie, Canada | |
| 14-39 | Robust Visual Analysis for Planogram Compliance Problem | 576 |
| Anurag Saran, Ehtesham Hassan, Avinash Kumar Maurya, India | |
Session 15: Person |
| 15-1 | Tri-Subjects Kinship Verification: Understanding the Core of a Family | 580 |
| Xiaoqian Qin, Xiaoyang Tan, Songcan Chen, China | |
| 15-2 | Estimation of Face Parameters Using Correlation Analysis and a Topology Preserving Prior | 584 |
| Stella Grasshof, Hanno Ackermann, Jörn Ostermann, Germany | |
| 15-3 | People Re-Identification Using Two-Stage Transfer Metric Learning | 588 |
| Guanwen Zhang, Jien Kato, Yu Wang, Kenji Mase, Japan | |
|
|
|
| Author Index |
592 |
|
|
|
