TABLE OF CONTENTS

Monday, May 8, 2017

Session 1: Inspection

01-01Real-Time Image Improvement System for Visual Testing of Nuclear Reactors1
Naoki Hosoya, Atsushi Miyamoto, Junichirou Naganuma, Japan
01-02Damage Detection from Aerial Images via Convolutional Neural Networks5
Aito Fujita, Ken Sakurada, Tomoyuki Imaizumi, Riho Ito, Shuhei Hikosaka, Ryosuke Nakamura, Japan
01-03In-Line Recognition of Agglomerated Pharmaceutical Pellets with Density-Based Clustering and Convolutional Neural Networkcva
Andraž Mehle, Boštjan Likar, Dejan Tomaževič, Slovenia[Springer page]
01-04A Fast Sparse Reconstruction Approach for High Resolution Image-Based Object Surface Anomaly Detection9
Woon Huei Chai, Shen-Shyang Ho, Chi-Keong Goh, Liang-Tien Chia, Hiok Chai Quek, Singapore

Session 2: 3D

02-01Plane Labeling Trinocular Stereo Matching with Baseline Recovery13
Luis Horna, Robert Fisher, United Kingdom[attachment]
02-02Estimating Extrinsic Parameters Between a Stereo Rig and a Multi-Layer Lidar Using Plane Matching and Circle Feature Extraction17
Trevor Gee, Jason James, Wannes Van Der Mark, Alfonso Gastelum Strozzi, Patrice Delmas, Georgy Gimel'farb, New Zealand
02-03Selecting Image Pairs for SfM by Introducing Jaccard Similaritycva
Takaharu Kato, Ikuko Shimizu, Tomas Pajdla, Japan[Springer page]
02-04Incremental Structural Modeling on Sparse Visual SLAMcva
Rafael Roberto, Hideaki Uchiyama, João Lima, Hajime Nagahara, Rin-ichiro Taniguchi, Veronica Teichrieb, Brazil[Springer page]

Session 3: IAPR Distinguished Lecture 1

03-01Direct Methods for 3D Reconstruction and Visual SLAM21
Daniel Cremers, Germany

Session 4: Poster 1

04-01Histogram of Oriented Gradients Based Presentation Attack Detection in Dorsal Hand-Vein Biometric System26
Shruti Bhilare, Vivek Kanhangad, Narendra Chaudhari, India
04-02Compressive Color Sensing Using Random Complementary Color Filter Array30
Satoshi Satou, Nobuhiko Wakai, Kunio Nobori, Takeo Azuma, Takamichi Miyata, Makoto Nakashizuka, Japan
04-03The Autonomous Hidden Camera Crew34
Timothy Callemein, Wiebe Van Ranst, Toon Goedemé, Belgium
04-04Supervised Multi-Modal Dictionary Learning for Clothing Representation38
Qilu Zhao, Jiayan Wang, Zongmin Li, China
04-05Asymmetric Locality Preserving Projection and Its Application to K-Nearest Neighbor Method42
Yoshio Iwai, Masashi Nishiyama, Hiroki Yoshimura, Japan
04-06Evaluation of Features for SVM-Based Classification of Geometric Primitives in Point Clouds46
Pascal Laube, Matthias O. Franz, Georg Umlauf, Germany
04-07Design and Analysis of a Novel Omnidirectional Stereovision System50
Lei Luo, Zhiyu Xiang, China
04-08A Framework for an Accurate Point Cloud Based Registration of Full 3D Human Body Scans54
Vladislav Golyanik, Reis Gerd, Bertram Taetz, Didier Stricker, Germany[attachment]
04-09A Visual-SLAM for First Person Vision and Mobile Robots60
Takahiro Terashima, Osamu Hasegawa, Japan
04-10Enhancing Discriminability of Randomized Time Warping for Motion Recognition64
Lincon Sales De Souza, Bernardo Gatto, Kazuhiro Fukui, Japan
04-11Activity Recognition for Indoor Fall Detection Using Convolutional Neural Network68
Kripesh Adhikari, Hamid Bouchachia, Hammadi Nait-Charif, United Kingdom
04-12Recognition of JSL Finger Spelling Using Convolutional Neural Networks72
Hana Hosoe, Shinji Sako, Bogdan Kwolek, Japan
04-13Quadrant Segmentation and Ring-Like Searching Based FPGA Implementation of ORB Matching System for Full-HD Video76
Tianmin Rao, Takeshi Ikenaga, Japan
04-14A Fast Algorithm for a Weighted Low Rank Approximation80
Aritra Dutta, Xin Li, United States of America
04-15Dynamic Hand Gesture Recognition from Cyclical Hand Pattern84
Huong-Giang Doan, Hai Vu, Thanh-Hai Tran, Vietnam
04-16Road User Detection with Convolutional Neural Networks: an Application to the Autonomous Shuttle WEpod88
Floris Gaisser, Pieter P. Jonker, Netherlands
04-17Detection of Cars in Complex Urban Areas92
Mohamed ElMikaty, Tania Stathaki, United Kingdom
04-18Unsupervised Place Discovery for Visual Place Classification96
Xiaoxiao Fei, Kanji Tanaka, Kouya Inamoto, Guoqing Hao, Japan
04-19Sheet Metal Forming Limits as Classification Problem100
Christian Jaremenko, Xiaolin Huang, Emanuela Affronti, Marion Merklein, Andreas Maier, Germany
04-20Human Ear Structure from Motion104
Salah Eddine Kabbour, Pierre-Yves Richard, France[attachment]
04-21Skeletonization and 3D Graph Approach for Thin Objects Recognition in Pick and Place Tasks108
Pierre Willaume, Pierre Parrend, Etienne Gancel, Aline Deruyver , France
04-223D Convolutional Object Recognition Using Volumetric Representations of Depth Data112
Ali Caglayan, Ahmet Burak Can, Turkey[attachment]
04-23Bi-Direction ICP: Fast Registration Method of Point Clouds116
Shiqiang Guan, Guolin Li, Xiang Xie, Zhihua Wang, China[attachment]
04-24Model Based Visual Inspection of Pharmaceutical Tablets with Photometric Stereo120
Gregor Podrekar, Dejan Tomaževič, Boštjan Likar, Peter Usenik, Slovenia
04-25Domain Adaptation of Articulated Pose Estimation via Synthetic Pose Prior124
Kazuhiko Murasaki, Haruka Yonemoto, Kyoko Sudo, Tetsuya Kinebuchi, Japan
04-26Unsupervised Image Segmentation Using Defocus Map and Superpixel Grouping128
Chun-Kuei Lo, Long-Wen Chang, Taiwan
04-27A PTZ Camera Based People-Occupancy Estimation System (PCBPOES)132
Arun Kumar Chandran, Aravind Subramanian, Wai Choong Wong, Junjing Yang, Karn Ashokkumar Chaturvedi, Singapore
04-28Development of Online Machine Vision System Using Support Vector Regression (SVR) Algorithm for Grade Prediction of Iron Ores136
Ashok Kumar Patel, Snehamoy Chatterjee, Amit Kumar Gorai, India
04-29Single Image Super Resolution Based on Content-Aware Constraint and Intensity-Order Constraint140
Takashi Shibata, Atsushi Sato, Japan
04-30Real-Time Recognition of Sign Language Gestures and Air-Writing Using Leap Motion144
Pradeep Kumar, Rajkumar Saini, Santosh Kumar Behera, Debi Prosad Dogra, Partha Pratim Roy, India
04-31Field Tests on Flat Ground of an Intensity-Difference Based Monocular Visual Odometry Algorithm for Planetary Rovers148
Geovanni Martinez, Costa Rica

Session 5: Feature/Similarity

05-01Convolutional Bag of Words for Diabetic Retinopathy Detection from Eye Fundus Imagescva
Pedro Costa, Aurélio Campilho, Portugal[Springer page]
05-02Mobile Hologram Verification with Deep Learningcva
Daniel Soukup, Reinhold Huber-Mörk, Austria[Springer page]
05-03Object Specific Deep Feature and Its Application to Face Detection152
Xianxu Hou, Jiasong Zhu, Ke Sun, Linlin Shen, Guoping Qiu, China
05-04Crowd Pedestrian Detection Using Expectation Maximization with Weighted Local Features156
Shih-Shinh Huang, Chun-Yuan Chen, Taiwan
05-05Fast Search Based on Generalized Similarity Measurecva
Yuzuko Utsumi, Tomoya Mizuno, Masakazu Iwamura, Koichi Kise, Japan[Springer page]
05-06Deep Visual Words: Improved Fisher Vector for Image Classification160
Ali Diba, Ali Mohammad Pazandeh, Luc Van Gool, Belgium

Tuesday, May 9, 2017

Session 6: Recognition/Classification

06-01Computational Single-Cell Classification Using Deep Learning on Bright-Field and Phase Images164
Nan Meng, Hayden K. H. So, Edmund Y. Lam, China
06-02Hierarchical Zero-Shot Classification with Convolutional Neural Network Features and Semantic Attribute Learning168
Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang, United States of America
06-03Simultaneous Estimation of Food Categories and Calories with Multi-Task CNN172
Takumi Ege, Keiji Yanai, Japan
06-04Mass-Produced Parts Traceability System Based on Automated Scanning of "Fingerprint of Things"176
Toru Takahashi, Yuta Kudo, Rui Ishiyama, Japan
06-05A New Deep Learning Architecture for Detection of Long Linear Infrastructure181
Jayavardhana Gubbi, Ashley Varghese, Balamuralidhar P., India
06-06Automatic Extraction and Recognition of Shoe Logos with a Wide Variety of Appearance185
Kazunori Aoki, Wataru Ohyama, Tetsushi Wakabayashi, Japan

Session 7: Gaze/FPV

07-01Attention to Describe Products with Attributes189
Shuohao Li, Kota Yamaguchi, Takayuki Okatani, China
07-02A New Reconstruction Method in Gaze Estimation with Natural Head Movement193
Yi Liu, Bu-Sung Lee, Martin McKeown, Singapore
07-03Hotspots Detection for Machine Operation in Egocentric Vision197
Longfei Chen, Kazuaki Kondo, Yuichi Nakamura, Dima Damen, Walterio W. Mayol-Cuevas, Japan
07-04Point of Gaze Estimation Using Corneal Surface Reflection and Omnidirectional Camera Image201
Taishi Ogawa, Atsushi Nakazawa, Toyoaki Nishida, Japan

Session 8: IAPR Distinguished Lecture 2

08-01Connecting the Dots: Embodied Visual Perception from First-person Cameras205
Jianbo Shi , United States of America

Session 9: Poster 2

09-01Two-Stage Model Fitting Approach for Human Body Shape Estimation from a Single Depth Image208
Mei Oyama, Naoshi Kaneko, Masaki Hayashi, Kazuhiko Sumi, Takeshi Yoshida, Japan
09-02An Incremental Face Recognition System Based on Deep Learning212
Lufan Li, Zhang Jun, Jiawei Fei, Shuohao Li, China
09-03Continuous Action Recognition with Weakly Labelling Videos216
Jun Lei, Guohui Li, Jun Zhang, Shuohao Li, Fenglei Wang, China
09-04Scene Text Extraction with Local Symmetry Transform220
Qi Chen, Yonghong Song, Yuanlin Zhang, China
09-05Event Based Surveillance Video Synopsis Using Trajectory Kinematics Descriptors224
Wei-Cheng Wang, Pau-Choo Chung, Chun-Rong Huang, Wei-Yun Huang, Taiwan
09-06Can Fully Convolutional Networks Perform Well for General Image Restoration Problems?228
Subhajit Chaudhury, Hiya Roy, Japan
09-07High Accuracy Local Stereo Matching Using DoG Scale Map232
Masamichi Kitagawa, Ikuko Shimizu, Radim Sara, Japan
09-08Initial Response Time Measurement in Eye Movement for Dementia Screening Test236
Tamotsu Endo, Norimichi Ukita, Hiroki Tanaka, Norihiro Hagita, Satoshi Nakamura, Hiroyoshi Adachi, Manabu Ikeda, Hiroaki Kazui, Takashi Kudo, Japan
09-09Improving the Performance of Non-Rigid 3D Shape Recovery by Points Classification240
Junjie Hu, Terumasa Aoki, Japan
09-10Retinal Vessel Enhancement via Sparse Coding and Dictionary Learning244
Bangzhong Gu, Bin Chen, Limin Luo, China
09-11A Raspberry Pi 2-Based Stereo Camera Depth Meter248
James Cooper, Mihailo Azhar, Trevor Gee, Wannes Van Der Mark, Patrice Delmas, Georgy Gimel'farb, New Zealand
09-12Detection of View-Disturbing Noise by Using Time-Axial Clustering in Spatio-Temporal Image252
Taichi Arimasa, Hiromi Yoshida, Youji Iiguni, Japan
09-13Automatic Pencil Sketch Generation by Using Canny Edges256
Ryota Okawa, Hiromi Yoshida, Youji Iiguni, Japan
09-14FPGA Implementation of High Frame Rate and Ultra-Low Delay Vision System with Local and Global Parallel Based Matching260
Tingting Hu, Takeshi Ikenaga, Japan
09-15Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project264
Mohammad Eshghi, Holger Roth, Masahiro Oda, Min Suk Chung, Mori Kensaku, Japan
09-16Multi-Layer Age Regression for Face Age Estimation268
Choon Ching Ng, Yi-Tesng Cheng, Gee-Sern Hsu, Moi Hoon Yap, Singapore
09-17Projective Structure from Facial Motion272
Stella Graßhof, Hanno Ackermann, Felix Kuhnke, Jörn Ostermann, Sami Sebastian Brandt, Germany
09-18Mixture Particle Filter with Block Jump Biomechanics Constraint for Volleyball Players Lower Body Parts Tracking276
Fanglu Xie, Xina Cheng, Takeshi Ikenaga, Japan
09-19Detecting Humans in RGB-D Data with CNNs280
Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi, United Kingdom
09-20Deep Convolutional Neural Networks for Motion Instability Identification Using Kinect284
Daniel Leightley, Subhas C. Mukhopadhyay, Hemant Ghayvat, Moi Hoon Yap, United Kingdom
09-21Fast Signature Spotting in Continuous Air Writing288
Santosh Kumar Behera, Pradeep Kumar, Debi Prosad Dogra, Partha Pratim Roy, India
09-22Human Bodypart Classification Using Geodesic Descriptors and Random Forests292
Sebastian Handrich, Ayoub Al-Hamadi, Erik Lilienblum, Zuofeng Liu, Germany
09-23Low Cost Calibration of Stereo Line Scan Camera Systems296
Erik Lilienblum, Sebastian Handrich, Ayoub Al-Hamadi, Germany
09-24Two Features Combination with Gated Recurrent Unit for Visual Speech Recognition300
Masaya Iwasaki, Michiko Kubokawa, Takeshi Saitoh, Japan
09-25Transfer Learning of a Deep Convolutional Neural Network for Localizing Handwritten Slab Identification Numbers304
Sang Jun Lee, Gyogwon Koo, Hyeyeon Choi, Sang Woo Kim, Korea, South
09-26Multi-Resolution ICP for the Efficient Registration of Point Clouds Based on Octrees308
Michiel Vlaminck, Hiep Luong, Wilfried Philips, Belgium
09-27Weak Rocks Disintegration Patterns Recognition through Image Analysis312
Orlando Rincón, Manuel Ocampo, Colombia
09-28Fast Low-Level Multi-Scale Feature Extraction for Hexagonal Images316
S. A. Coleman, B. W. Scotney, B. Gardiner, United Kingdom
09-29Multiscale Two-View Stereo Using Convolutional Neural Networks for Unrectified Images320
Pramod Yadati, Anoop Namboodiri, India[attachment]
09-30Texture Super-Resolution for 3D Reconstruction324
Calum Burns, Aurélien Plyer, Frédéric Champagnat, France
09-31Detection of Self Intersection in Synthetic Hand Pose Generators328
Shome Subhra Das, India

Session 10: Image Processing

10-01Parsing Floor Plan Images332
Samuel Dodge, Jiu Xu, Björn Stenger, Japan[attachment]
10-02Pixel-Wise Binarization of Musical Documents with Convolutional Neural Networks336
Jorge Calvo-Zaragoza, Gabriel Vigliensoni, Ichiro Fujinaga, Spain
10-03Limited Memory Switched Broyden Method for Faster Image Deblurring340
Robby Haelterman, Ichraf Lahouli, Michal Shimoni, Joris Degroote, Belgium
10-04Self-Learning Structure for Text Localization344
Supakorn Intaratat, Karn Patanukhom, Thailand

Wednesday, May 10, 2017

Session 11: Tracking/ITS

11-01Active Discriminative Tracking Using Collective Memory348
Kourosh Meshgi, Shigeyuki Oba, Shin Ishii, Japan
11-02Deep Residual Coalesced Convolutional Network for Efficient Semantic Road Segmentationcva
Igi Ardiyanto, Teguh Bharata Adji, Indonesia[Springer page]
11-03A Neural Network Approach to Visual Tracking352
Zhe Zhang, Kin Hong Wong, Zhiliang Zeng, Lei Zhu, China
11-04A Surround View Image Generation Method with Low Distortion for Vehicle Camera Systems Using a Composite Projection356
Kunio Nobori, Norimichi Ukita, Norihiro Hagita, Japan[attachment]
11-05Ball-Like Observation Model and Multi-Peak Distribution Estimation Based Particle Filter for 3D Ping-Pong Ball Tracking360
Ziwei Deng, Xina Cheng, Takeshi Ikenaga, Japan

Session 12: Face

12-01Exemplar-Based Human Facial Features Cloning364
Damon Shing-Min Liu, Feng-Yi Lin, Taiwan
12-02Face Liveness Detection with Feature Discrimination Between Sharpness and Blurriness368
Chun Hsiao Yeh, Herng-Hua Chang, Taiwan
12-03Analysis of In- and Out-group Differences between Western and East-Asian Facial Expression Recognition372
Gibran Benitez-Garcia, Tomoaki Nakamura, Masahide Kaneko, Japan

Session 13: IAPR Distinguished Lecture 3

13-01Image Recognition for Driver Assistance in Intelligent Vehicles376
Hiroshi Murase , Japan

Session 14: Poster 3

15-01Model-Based 3D Pose Estimation for Pick-and-Place Application382
Shih-Cheng Liang, Huei-Yung Lin, Chin-Chen Chang, Taiwan
15-02Pedestrian Near-Miss Analysis on Vehicle-Mounted Driving Recorders386
Teppei Suzuki, Yoshimitsu Aoki, Hirokatsu Kataoka, Japan
15-03Two-Stage Cross-Based Stereo Disparity Refinement390
Zhonglin Xu, Sei-ichiro Kamata, Qieshi Zhang, Japan[attachment]
15-04Multiple-Organ Segmentation by Graph Cuts with Supervoxel Nodes394
Toshiya Takaoka, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan
15-05Phenotyping of Xylem Vessels for Drought Stress Analysis in Rice398
Swati Bhugra, Anupama Anupama, Santanu Chaudhury, Brejesh Lall, Archana Chugh, India[attachment]
15-06An MRF-Based Image Segmentation with Unsupervised Model Parameter Estimation402
Yoshihiko Toya, Hiroyuki Kudo, Japan
15-07A Deep Network Model Based on Subspaces: A Novel Approach for Image Classification406
Bernardo Bentes Gatto, Lincon Sales de Souza, Eulanda M. dos Santos, Brazil
15-08Banknote Portrait Detection Using Convolutional Neural Network410
Ryutaro Kitagawa, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Matsuki, Naotake Natori, Hiroshi Ishikawa, Japan
15-09A New Algorithm for Fast and Accurate Moving Object Detection Based on Motion Segmentation by Clustering414
Yuchi Zhang, Guolin Li, Xiang Xie, Zhihua Wang, China
15-10Unsupervised Video Object Segmentation by Supertrajectory Labeling418
Masahiro Masuda, Yoshihiko Mochizuki, Hiroshi Ishikawa, Japan
15-11Dilated Convolutions for Image Classification and Object Localization422
Yasunori Kudo, Yoshimitsu Aoki, Japan
15-12Pedestrian Positioning in Urban City with the Aid of Google Maps Street View426
Haitao Wang, Yanlei Gu, Shunsuke Kamijo, Japan
15-13Robust Markers for Visual Navigation Using Reed-Solomon Codes430
Jayavardhana Gubbi, Sandeep N. K., Pavan Kumar Reddy K., P. Balamuralidhar, India
15-14A Preliminary Study on Extracting Objects in Sketches434
Bo Huang, Jiansheng Chen, China
15-15A Sampling Method for Processing Contours Drawn with an Uncertain Stroke Order and Number438
Kazuya Ose, Kazunori Iwata, Nobuo Suematsu, Japan
15-16Estimation of Radial Distortion Using Local Spectra of Planar Textures442
Benjamin Spitschan, Jörn Ostermann, Germany
15-17Low-Resolution Person Recognition Using Image Downsampling448
Keiji Obara, Hiroki Yoshimura, Masashi Nishiyama, Yoshio Iwai, Japan
15-18Fast and Robust Selection of Highly-Correlated Features in Regression Problems452
Andreas Maier, Dalia Rodríguez-Salas, Germany
Xili Wang, Hu Li, Xiyuan Wang, China
15-20DFD2.0: Motion Robustness by Amplitude Domain Approach460
Takashi Kawamura, Khang Nguyen, Shunsuke Yasugi, Mitsuyoshi Okamoto, Motonori Ogura, Shinsaku Hiura, Japan
15-21A Linear Method for Recovering the Depth of Ultra HD Cameras Using a Kinect V2 Sensor464
Yuan Gao, Matthias Ziegler, Frederik Zilly, Sandro Esquivel, Reinhard Koch, Germany
Justine Seow Jia Wen, Ali Afzalian Mand, Malaysia
15-23Fast, Versatile, and Non-Destructive Biscuit Inspection System Using Spectral Imaging472
Jens Michael Carstensen, Denmark
15-24Fine-Grained Event Timing Detection Method Using Quasi-High Frame Generation for Single Camera Image Sequence476
Ayumi Matsumoto, Dan Mikami, Hideaki Kimata, Japan
15-25Saliency/non-Saliency Segregation in Video Sequences Using Perception-Based Local Ternary Pattern Features480
Kwok-Leung Chan, China
15-26Refining Faster-RCNN for Accurate Object Detection484
Myung-Cheol Roh, Ju-young Lee, Korea, South
15-27Visual-to-Speech Conversion Based on Maximum Likelihood Estimation488
Rina Ra, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki, Japan
15-28A Study of Virtual Visual Servoing Sensitivity in the Context of Image/GIS Registration for Urban Environments492
Hengyang Wei, Muriel Pressigout, Luce Morin, Myriam Servières, Guillaume Moreau, France
15-29Skin Beautification Detection Using Sparse Coding496
Tianyang Sun, Xinyu Hui, Zihao Wang, Shengping Zhang, China
15-30Robust Registration of Serial Cell Microscopic Images Using 3D Hilbert Scan Search500
Yongwen Lai, Sei-ichiro Kamata, Zhizhong Fu, Japan
15-31Wood Cellular Structure Evaluation Using Image Analysis Methods504
Jukka Antikainen, Finland
15-32Could You Guess an Interesting Movie from the Posters?: An Evaluation of Vision-Based Features on Movie Poster Database508
Yuta Matsuzaki, Kazushige Okayasu, Takaaki Imanari, Naomichi Kobayashi, Yoshihiro Kanehara, Ryousuke Takasawa, Akio Nakamura, Hirokatsu Kataoka, Japan