(1) |
09:00-09:05 |
開会挨拶(馬場口 登) |
10月25日(木) 午前 Keynote Speach 1 09:05 - 10:05 |
(2) |
09:05-10:05 |
Towards Highly Versatile Document Image Analysis |
○Henry Baird(Lehigh Univ.) |
|
10:05-10:20 |
休憩 ( 15分 ) |
10月25日(木) 午前 International Session 1 10:20 - 12:00 |
(3) |
10:20-10:45 |
Copyright Protection of Images Based on Large-Scale Image Recognition |
○Koichi Kise・Satoshi Yokota・Akira Shiozaki(Osaka Prefecture Univ.) |
(4) |
10:45-11:10 |
State-wise Potential Description for Modeling Relationships between Distant Nodes in Markov Random Fields |
○Younghee Kwon・Jin Hyung Kim(KAIST) |
(5) |
11:10-11:35 |
Video Classification Using Linear Subspace Methods |
○Kei Kikuchi・Seiji Hotta(Tokyo Univ. of Agri. and Tech.) |
(6) |
11:35-12:00 |
Combining Three Different Types of Local Features for Generic Object Recognition |
○Yasunori Kamiya(Nagoya Univ.)・Yoshikazu Yano(Aichi Inst. of Tech.)・Shigeru Okuma・Tomokazu Takahashi・Ichiro Ide・Hiroshi Murase(Nagoya Univ.) |
|
12:00-13:30 |
昼食 ( 90分 ) |
10月25日(木) 午後 Keynote Speach 2 座長: Hitoshi Sakano 13:30 - 14:30 |
(7) |
13:30-14:30 |
Pattern recognition: the edge of science, from the viewpoint of science fiction |
○Hideaki Sena(Tohoku Univ.) |
|
14:30-15:00 |
休憩 ( 30分 ) |
10月25日(木) 午後 Invited Talks Session 15:00 - 16:30 |
(8) |
15:00-15:30 |
A Road Map to Active Eyes
-- Geometry and Photometry Aspect and Prospect of Robotics Vision -- |
○Koichiro Deguchi(Tohoku Univ.) |
(9) |
15:30-16:00 |
Business Opportunity and Technical Hurdles of Pattern Recognition in the Internet Portal Company |
○Jae bum Lee(NHN) |
(10) |
16:00-16:30 |
Computer Vision for Virtual/Mixed Reality: Trends and Perspectives |
○Hideo Saito(Keio Univ.) |
|
16:30-16:40 |
休憩 ( 10分 ) |
10月25日(木) 午後 Keynote Speach 3 16:40 - 17:40 |
(11) |
16:40-17:40 |
Creating Special Effects in film Utilizing 3D Graphics and Pattern Recofnition Technology |
○Manjae Lee(ETRI) |
|
17:40-17:50 |
休憩 ( 10分 ) |
10月25日(木) 午後 International Session 2 17:50 - 19:05 |
(12) |
17:50-18:15 |
Extraction of Structure of Silhouette Images by Weighted Minimum Common Supergraph |
○Tomo Miyazaki・Shinichiro Omachi・Hirotomo Aso(Tohoku Univ.) |
(13) |
18:15-18:40 |
Time Series Data Mining and Behavioral Recognition for Computer Games Player Modeling and Adaptation |
○Chee-Onn Wong・Jongin Kim・Jongyeol Yang・Keechul Jung(Soongsil Univ.) |
(14) |
18:40-19:05 |
Image Registration Method of Multiple Motion-Regions and Its Applications |
SoonKeun Chang・○Masao Shimizu・Masatoshi Okutomi(Tokyo Inst. of Tech.) |
|
19:30-21:30 |
懇親会 ( 120分 ) |
10月26日(金) International Session 3 09:55 - 10:45 |
(15) |
09:55-10:20 |
UML based Data Model and Process for Efficient Integration of Heterogeneous Highway Traffic Image Data |
○Yoon-Hyuk Choi・Segil Jeon・Seong Namkoong(Expressway & Transportation Tech.Inst.) |
(16) |
10:20-10:45 |
Simulator for Measuring Elderly Visual Performances While Driving |
○Tomoaki Adachi・Hiroshi Yamamoto(Meijo Univ.)・Muneo Yamada(NAGOYA ELECTRIC WORKS)・Mikiko Kawasumi(Aichi Shukutoku Univ.)・Osami Yamamoto・Tomoaki Nakano・Shin Yamamoto(Meijo Univ.) |
10月26日(金) 午前 日本語セッション 1 09:30 - 10:45 |
(17) |
09:30-09:55 |
ヒストグラムを用いたピクセル生成モデルにもとづく逐次モンテカルロ動画像追跡 |
○宮島雄一(早大)・松井 淳(NHK/早大)・中田洋平・松本 隆(早大) |
(18) |
09:55-10:20 |
RFIDタグとカメラ映像を用いたサーベイランス映像中の人物同定 |
○中嶋大介・伊藤義道・新田直子・馬場口 登(阪大) |
(19) |
10:20-10:45 |
フレームクラスタリングを利用したCGM動画像コンテンツ検索手法の提案 |
○帆足啓一郎・上向俊晃・松本一則・菅谷史昭(KDDI研) |
|
10:45-11:00 |
休憩 ( 15分 ) |
10月26日(金) 午前 International Session 4 11:00 - 11:50 |
(20) |
11:00-11:25 |
Study on Recognition / Decision Performance Measurement System for Assessment of Elderly Driver's Ability |
○Hisayuki Tanahashi・Tatsuomi Noda(Meijou Univ.)・Muneo Yamada(Nagoya Electric Works)・Mikiko Kawasumi(Aichi Shukutoku Univ.)・Osami Yamamoto・Shin Yamamoto・Tomoaki Nakano(Meijou Univ.) |
(21) |
11:25-11:50 |
Traffic Sign Recognition Using Color Histogram and Mutual Information |
○Sunworl Kim(Chonnam National Univ.)・Wanhyun Cho・Myungeun Lee(Chonnam National Univ)・Soohyung Kim(Chonnam National Univ.)・Soonyoung Park(Mokpo National Univ.) |
10月26日(金) 午前 日本語セッション 2 11:00 - 11:50 |
(22) |
11:00-11:25 |
情景内カラー文字の最適2値化と変形耐性認識の検討 |
○横林 実・若原 徹(法政大) |
(23) |
11:25-11:50 |
k-meansクラスタリングと固有空間外れ値検出器を用いた欠陥検出 |
○天野敏之(奈良先端大) |
|
11:50-12:50 |
昼食 ( 60分 ) |
10月26日(金) 午後 International Session 5 12:50 - 14:05 |
(24) |
12:50-13:15 |
Hands Gesture Recognition Based on Dynamic Bayesian Network Framework |
○Heung-Il Suk・Bong-Kee Sin・Beom-Joon Cho(Pukyong National Univ) |
(25) |
13:15-13:40 |
Accurate, Real-time 3D Reconstruction of Human Postures from Orthogonal Images Based on Neural Networks |
Dong-Wan Kang(Waseda Univ.)・Zhongze Chan(Univ. of South China)・○Jun Ohya(Waseda Univ.) |
(26) |
13:40-14:05 |
Body-part Segmentation fro a Real Human Wearing Multiple-Colored Suit by a Mean Shift Based Algorithm |
Huimin Guo・Jun Okazaki・Dong-Wan Kang・○Jun Ohya(Waseda Univ.) |
10月26日(金) 午後 International Session 6 12:50 - 14:30 |
(27) |
12:50-13:15 |
Segmentation of On-line Handwritten Japanese Characters of Arbitrary Line Direction Using SVM |
Bilan Zhu・○Masaki Nakagawa(Tokyo Univ. of Agriculture and Tech.) |
(28) |
13:15-13:40 |
Staff-Line Detection and Removal Algorithm for a Camera-Based Recognition of Music Score Images |
○Soo-Hyung Kim・Hwa-Jeong Son・Sung-Ryul Oh・Chil-Woo Lee(Chonnam National Univ.)・Il-Seok Oh(Chonbuk National Univ.) |
(29) |
13:40-14:05 |
An Attempt of CUDA Implementation of PCA-SIFT |
Masakazu Iwamura・○Takayuki Hondo・Kazuto Noguchi・Koichi Kise(Osaka Pref. Univ.) |
(30) |
14:05-14:30 |
Signboard Recognition by Consistency Checking of Local Features |
○Jihoon Kim・Taik Heon Rhee・Kee-Eung Kim・Jin Hyung Kim(KAIST) |
|
14:30-14:45 |
休憩 ( 15分 ) |
10月26日(金) 午後 International Session 7 14:45 - 16:25 |
(31) |
14:45-15:10 |
Automatic Region-of-Interest Extraction from Dental Panoramic Radiographs for Forensic Personal Identification |
○Febriliyan Samopa・Akira Asano・Akira Taguchi(Hiroshima Univ.) |
(32) |
15:10-15:35 |
Detecting Abandoned Luggage using Bayesian Inference and Finite State Automaton |
○Sooyeong Kwak・Guntae Bae・Hyeran Byun(Yonsei Univ.) |
(33) |
15:35-16:00 |
Color Image Classification Using Block Image Replacement and Local Averaging Classifier |
○Kazuki Kondo・Seiji Hotta(Tokyo Univ. of Agri. and Tech.) |
(34) |
16:00-16:25 |
Garbage Model Formulation for Sign Language Spotting with Conditional Random Fields |
○Hee-Deok Yang・Seong-Whan Lee(Korea Univ.) |
10月26日(金) 午後 International Session 8 14:45 - 16:30 |
(35) |
14:45-15:10 |
PCA-Based Personal Favorite Scene Selection from Broadcast Soccer Video |
○Masao Izumi(Osaka Prefecture Univ.) |
(36) |
15:10-15:35 |
Image Retrieval based on Object Extraction and Kansei Estimation |
○Nanik Suciati(Hiroshima Univ. / ITS)・Darlis Herumurti・Joko Lianto Buliali・Dyah Wardhani Kusuma・Ahmad Saikhu(ITS)・Chie Muraki Asano・Akira Asano(Hiroshima Univ.) |
(37) |
15:35-16:00 |
Depth Estimation from Two Vanishing Points |
○Jinsu Jo・Jongwon Han・Yillbyung Lee(Yonsei Univ.) |
(38) |
16:00-16:25 |
The architecture of device that manipulates image in which each set of activities is ignited through transference of impulses |
○Shinji Karasawa(Miyagi Kosen)・Masatoshi Iwamoto(Tohoku Gakuin Univ.) |
(39) |
16:25-16:30 |
閉会催札(Bong-Kee Sin) |