The 15th International Conference on Vision Interface
May 27-29, 2002, Calgary, Canada

Final Program

Registration & Welcome reception
May 26, Sunday, 19:00-21:00
in Information Communication Technology Building (ICT) 516 - map

Official Opening on May 27, Monday at 8:50 at ICT 121.

  May 27 Monday May 28 Tuesday May 29 Wednesday
08:30 -08:50 Morning tea
08:50 -10:30 V1. Image Coding and
Object Representation
V4. Pattern Recognition and Document Analysis V6. Face Recognition and
3D Head Models
10:30 -11:00 Morning Break
11:00 -12:00 Invited Speaker
John Aloimonos
Invited Speaker
Matthew Turk
Invited Speaker
Gary Bradski
12:00 -13:30 Lunch
13:30 -15:35 V2. Tracking and Visual Surveillance V5. Single-Camera Vision:
Structure from Motion
V7. Vision-based Perceptual User Interfaces
15:30 -16:00 Afternoon Break
16:00 -18:05 V3. Multiple-Camera Vision: Matching, Stereo POSTER & DEMO
V8. Texture Analysis and
18:00 -19:00 Electronic Theatre (by GI) CIPPRS meeting
(everybody's welcome)
19:00 -21:00   Banquet. Award Presentation  

May 27 Monday

Session V1: Image Coding and Retrieval, Object Representation
Chair:  Minas Spetsakis
Oral Presentations
08:50 -09:15 s1-1. An Adaptive-Sampling Algorithm for Object Representation.
Robert Alterson, Minas Spetsakis (York U, Canada)
09:15 -09:40 s1-2. Region-Based Image Retrieval using Wavelet Transform.
Nobuo Suematsu, Yoshihiro Ishida, Akira Hayashi, Toshihiko Kanbara (Hiroshima City U and Fuji-film Software Corp., Japan)
09:40 -10:05 s1-3. Semantics Retrieval by Content and Context of Image Regions.
Wei Wang, Yuqing Song, Aidong Zhang (State U of New York at Buffalo, USA)
10:05 -10:30 s1-4. Visual Abstraction of Wildlife Footage using Gaussian Mixture Models
David Gibson, Neill Campbell, Barry Thomas (U of Bristol, UK)
Invited Talk
11:00 -12:00 Geometry and Statistics of Visual Space-Time.
Cornelia Fermueller, Patrick Baker, Yiannis Aloimonos (U of Maryland at College Park, USA )
Session V2: Tracking, Visual Surveillance, Omnidirectional Vision
Chair: Mark Fiala
Oral Presentations
13:30 -13:55 s2-1. Motion Segmentation and Tracking.- [demo]
King Yuen Wong, Minas E. Spetsakis (York U, Canada)
13:55 -14:20 s2-2. Automated Visual Surveillance Using Hidden Markov Models. - [demo]
Vinod Nair, James J. Clark (McGill U, Canada) 
14:20 -14:45 s2-3. Real-Time Tracking for Visual Interface Applications in Cluttered and Occluding Situations. - [demo]
David J. Bullock, John S. Zelek (U of Guelph, Canada)
14:45 -15:10 s2-4. Multi-object Motion Pattern Classification for Visual Surveillance and Sports Video Retrieval.
Akira Hayashi, Ryuji Nakasima, Toshihiko Kanbara, Nobuo Suematsu (Hiroshima City U, Japan)
15:10 -15:35 s2-5. A Novel Probability Model for Background Maintenance and Subtraction.
Dongsheng Wang, Tao Feng Harry Shum, Songde Ma (Microsoft Research Asia and Ac. Sc., China)
Session V3: Multiple-camera vision: Matching and Stereo
Chair: Gerhard Roth 
Oral Presentations
16:00 -16:25 s3-1. An Empirical Study of Some Feature Matching Strategies. - [demo]
Etienne Vincent and Robert Laganiere (U of Ottawa, Canada)
16:25 -16:50 s3-2. A Fast Area-Based Stereo Matching Algorithm. - [demo]
Luigi Di Stefano, Massimiliano Marchionni, Stefano Mattoccia, Giovanni Neri (U of Bologna, Italy)
16:50 -17:15

s3-3. Three-dimensional structure calculation: achieving accuracy without calibration.
B. Boufama, A. Habed (U of Windsor, Canada)

17:15 -17:40 s3-4. A Stereo Confidence Metric Using Single View Imagery.
Geoffrey Egnal, Max Mintz (U of Pennsylvania, USA), Richard P. Wildes (York U, Canada)
17:40 -18:05 s3-5. Limiting the Search Range of Correlation Stereo Using Silhouettes.
Geoffrey Egnal, Max Mintz, Kostas Daniilidis (U of Pennsylvania, Canada)

May 28 Tuesday

Session V4: Pattern recognition and document analysis   
Chair:  Jim Parker   
Oral Presentations
08:50 -09:15 s4-1. Reconnaissance En-ligne de Caractères Arabes Manuscrits par un Réseau de Kohonen.
Neila Mezghani, Amar Mitiche (INRS-Télécommunications, Canada)
09:15 -09:40 s4-2. Improved Method of Handwritten Digit Recognition Teseted on MNIST Database.
Ernst Kussul, Tatyana Baidyk (UNAM, Centro de Instrumentos, Mexico)
09:40 -10:05

s4-3. Combination of Decisions by Multiple Document Object Locators. - [demo]
Jung Soh (Electronics and Telecommunications Research Institute, Korea)

10:05 -10:30 s4-4. Simulating Eye Movement in Reading using Short-term Memory.
Satoru Morita (Yamaguchi U, Japan)
Invited Talk
11:00 -12:00 TLA Based Face Tracking
Matthew Turk et al (U of California at Santa Barbara, USA)
Session V5: Single-camera vision: Structure from Motion, Optical Flow, Calibration.
Chair: John Barron
Oral Presentations
13:30 -13:55 s5-1. Simultaneous Computation of Defocus Blur and Apparent Shifts in Spatial Domain.
Francois Deschenes, Djemel Ziou, Philippe Fuchs (U de Sherbrooke, Canada and Ecole des Mines de Paris, France)
13:55 -14:20 s5-2. Stable Recovery of Shape and Motion from Partially Tracked Feature Points with Fast Nonlinear Optimization.
Akira Amano, Tsuyoshi Migita, Naoki Asada (Hiroshima City U, Japan)
14:20 -14:45 s5-3. Reconstructing Depth from Spatiotemporal Curves.
Rui Rodrigues, António Ramires Fernandes, Kees van Overveld, Fabian Ernst (U. do Minho, Portugal and Philips Research, The Netherlands)
14:45 -15:10 s5-4. An Iterative Method for Improving Bas-relief Ambiguity.
Sung-Kee Park, Munsang Kim, In So Kweon (Advanced Institute of Science and Technology, Korea)
15:10 -15:35 s5-5. Bayesian Real-Time Optical Flow.
John S. Zelek (University of Guelph)

Posters and Demos
May 28, Tuesday, 16:00-18:15

Poster layout information

s1-5. Real-Time Motion Estimation by Object-Matching for High-Level Video Representation. - [demo]
Aishy Amer, Amar Mitiche (INRS-Télécommunications, Canada), Eric Dubois (U d’Ottawa, Canada)

s1-6. Hierarchical Indexing Images Using Weighted Low Dimensional Texture Features.
Mira Park (U of NSW), Jesse S. Jin (U of Sydney), Laurence S. Wilson (CSIRO, Australia)

s1-7. Generation of Images of Historical Documents by Composition of their Components
Carlos A.B. Mello, Rafael D. Lins (UFPE, Brazil)

s2-6. Robot Navigation Using Panoramic Landmark Tracking. - [demo]
Mark Fiala, Anup Basu (U of Alberta, Canada)

s2-7. Wavelet Based Resolution Enhancement of Omnidirectional Image.
Peng Qimin, Jia Yunde (Beijing Institute of Technology, China)

s2-8. The Detection of Obstacles Using Features by the Horizon View Camera.
Ayami Iwata, Kunihito Kato, Kazuhiko Yamamoto (Gifu U, Japan)

s3-6. Towards a fast and reliable dense matching algorithm.
K. Jin and B. Boufama (U of Windsor, Canada)

s4-5. Road Sign Recognition by Single Positioning of Space-Variant Sensor Window.
D.G. Shaposhnikov, L.N. Podladchikova, A.V. Golovan, N.A. Shevtsova (Kogan Research Institute for Neurocybernetics, Rostov State U, Russia), K. Hong, X.W. Gao (Middlesex U, UK)

s4-6. Simple Distances Between Handwritten Signatures.
Jim R. Parker (U of Calgary, Canada)

s4-7. Hybrid System for Recognition of Handwritten Symbols on the Base of Structural Methods and Neural Networks.
R. Sadykhov, O. Malenko, A.N.Klimovich, M.L.Selinger  (Belarusian State U. and Ac. Sc., Belarus)

s5-6. A Thin Lens Based Camera Model for Depth Estimation from Blur and Translation by Zooming.
Masashi Baba, Naoki Asada, Ai Oda, Tsuyoshi Migita (Hiroshima City U, Japan)

s5-7. Retrieval of the Calibration Matrix from the 3-D Projective Camera Model.
Gamal H. Seedahmed and Toni Schenk (Photogrammetry Group, Ohio State U, USA)

s5-8. Camera Calibration with a Viewfinder.
Mohamed Bénallal and Jean Meunier (U de Montréal, Canada)

s6-2. N-Feature Neural Network Human Face Recognition.
Javad Haddadnia, Karim Faez, Majid Ahmadi (U of Windsor, Canada)

s6-6. Pose Error Effects on Range Sensing.
William Scott, Gerhard Roth, Jean-Francois Rivest (U of Ottawa and IIT-NRC, Canada)

s6-7. Estimating Expansion Rates from Range Data Sequences.
Hagen Spies (U of Heidelberg) and John Barron (U of Western Ontario, Canada)

s7-6. Affordable 3D Face Tracking Using Projective Vision. - [demo]
Dmitry O. Gorodnichy, Shahzad Malik, Gerhard Roth (CVG  IIT-NRC, Canada)

s7-7. Extraction of Hand Features for Recognition of Sign Language Words.
Nobuhiko Tanibata, Nobutaka Shimada, Yoshiaki Shirai (Osaka U, Japan)

s7-8. Robust Corner Tracking for Real-time Augmented Reality. - [demo]
Shahzad Malik, Gerhard Roth, Chris McDonald (CVG, IIT-NRC and Carleton U, Canada)

s8-6. A New Fast and Robust Circle Extraction Algorithm.
Euijin Kim, Miki Haseyame and Hideo Kitajima (Hokkaido U, Japan)

May 29 Wednesday

Session V6: Face Recognition, Head models, Biometrics,  
Chair: Ernst Kussul
Oral Presentations
08:50 -09:15 s6-1. Person Identification Technique Using Human Iris Recognition.
Christel-Loïc Tisse (Ast-Rousset Lab Stmicroelectronics), Lionel Torres, Michel Robert (Lirmm U de Montpellier, France)
09:15 -09:40 s6-3. Face Reconstruction From Shading Using Smooth Projected Polygon NN.
Mohamad Ivan Fanany, Masayoshi Ohno, Itsuo Kumazawa (Tokyo Institute of Technology, Japan)
09:40 -10:05 s6-4. 3D Head Models Retrieval Based on Hierarchical Facial Region Similarity.
Horace H. S. Ip, William Y F Wong (City U, Hong Kong)
10:05 -10:30 s6-5. Intrinsic Filtering of Range Images Using a Physically Based Noise Model.
Pierre Boulanger (U of Alberta, Canada), Olli Jokinen (Helsinki U of Technology, Finland), Angelo Beraldin (IIT-NRC, Canada)
Invited Talk
11:00 -12:00 OpenCV: Examples of Use and New Applications in Stereo, Recognition and Tracking
Gary Bradski (Vision, Graphics and Pattern Recognition Group, Intel Labs, USA)
Session V7: Vision-based Perceptual User Interfaces.  
Chair: Naoki Asada
Oral Presentations
13:30 -13:55 s7-1. Detection and Tracking of Eyes for Gaze-camera Control.  
Shinjiro Kawato, Nobuji Tetsutani (ATR Media Information Science Lab, Japan)
13:55 -14:20 s7-2. Nouse 'Use Your Nose as  a Mouse' - a New Technology for Hands-free Games and Interfaces. - [demo]
Dmitry O. Gorodnichy, Shahzad Malik, Gerhard Roth (Computational Video Group, IIT-NRC)
14:20 -14:45 7-3. Hand Shape Estimation Using Sequence of Multi-Ocular Images Based on Transition Network.
Yasushi Hamada, Nobutaka Shimada, Yoshiaki Shirai (Osaka U, Japan)
14:45 -15:10 s7-4. Robust Face Detection and Japanese Sign Language Hand Posture Recognition for Human-Computer Interaction in an "Intelligent" Room.
Jean-Christophe Terrillon, Arnaud Piplré, Yoshinori Niwa (Softopia Japan, Gifu), Kazuhiko Yamamoto (Gifu U)
15:10 -15:35 s7-5. Generation of Arm-gesture and Facial Expression for Intelligent Avatar Communications in the Internet.
Sang-Woon Kim (Carleton U, Canada), Young-Who Lee (Myongji U, Korea), Yoshinao Aoki (Hokkaido U, Japan)
Session V8: Texture Analysis and Segmentation .
Chair: Fathallah Nouboud
Oral Presentations
16:00 -16:25 s8-1. Algorithme Génétique et Critère de la Trace pour l'Optimisation du Vecteur Attribut : Application à la Classification Supervisée des Images de Textures.
M. Nasri, M. El Hitmy (Ecole Supérieure de Technologie, Maroc)
16:25 -16:50 s8-2. Geometrical and Topological Informations for Image Segmentation with Monte Carlo Markov Chain Implementation.
P. Bourdon, O. Alata, G. Damiand, C. Olivier, Y. Bertrand (Université de Poitiers, France)
16:50 -17:15 s8-3. Anisotropic Diffusion by a Recursive Linear Convolving Method: Application to Space-time Segmentation and Pattern Recognition.
Santiago V. Martinez, Juan M. Rendon Mancha, Georges Stamon (U René Descartes Paris V, France)
17:15 -17:40 s8-4. Histogram Characterization of Colored textures Using One-Dimensional Moments and Chromaticity Diagram.
Jacques Brochard, Majdi Khoudeir (Lab IRCOM-SIC, UMR-CNRS, France)
17:40 -18:05 s8-5. Granulometry Using Transformation Based Techniques.
Andrzej Zadorozny, Hong Zhang, Martin Jagersand (U of Alberta, Canada)


  • Each oral presentation is 25 min long: 20 min for the talk and  5 min for questions. 
  • All posters will be presented at the Poster-Demo Session on Tuesday. The authors will be provided with 1.2 m x 1.8 m boards and pins. In addition, should the authors like to show the results or demos using their laptops, they should contact the Program Chair  - the tables and the space will also be provided for those authors. 
  • The authors presenting posters may also be given an opportunity to present their work orally, should there be a time slot available at the appropriate session.
  • There is no difference between oral and poster papers in the proceedings.
  • Oral presentations will be held in Room ICT 121. The room is equipped with overhead projector and laptop computer. 
  • Posters should be set in Room ICT 116 starting 10:00 on Monday.

Last updated: 22 May 2002