ICIAR 2007 - Keynote Speakers

Keynote Speakers

Ching Suen
Concordia Chair in AI & Pattern Recognition
Director, CENPARMI
Concordia University, Canada
Homepage
Title: Recognition of Cell Phone Face Images
Date: August 22, 2007

Abstract »

This paper presents (a) a survey on current techniques in the recognition of face images, (b) characteristics of cell phone face images, and (c) a new method of processing and verifying faces captured by cell phones. It describes various methods of detecting local face recognition such as eyes, mouth, and nose, focussing on point distribution model and active shape models. An example will be given on the recognition of cell phone face images. The key points of these faces have been extracted by an active shape model, and the feature vector has been constructed by applying a Gabor filter to the face images. The One Class Support Vector Machine (OC-SVM) has been used to classify the Gabor features. The database consists of 1000 face images built from dozens of SVM machines.

This paper will be authored by Joanna Rokita, Adam Krzyzak, and Ching Suen
CENPARMI - Centre for Pattern Recognition & Machine Intelligence Concordia University, Montreal, Quebec H3G 1M8, Canada

Bio »

Ching Y. Suen received an M.Sc.(Eng.) degree from the University of Hong Kong and a Ph.D. degree from the University of British Columbia, Canada. In 1972, he joined the Department of Computer Science at Concordia University where he became Professor in 1979 and served as Chairman from 1980 to 1984, and as Associate Dean for Research of the Faculty of Engineering and Computer Science from 1993 to 1997. He has guided/hosted 70 visiting scientists and professors, and supervised 65 doctoral and master's graduates. Currently he holds the distinguished Concordia Research Chair in Artificial Intelligence and Pattern Recognition, and is the Director of CENPARMI, the Centre for PR & MI.

Prof. Suen is the author/editor of 11 books and more than 400 papers on subjects ranging from computer vision and handwriting recognition, to expert systems and computational linguistics. He is the founder of "The International Journal of Computer Processing of Oriental Languages" and served as its first Editor-in-Chief for 10 years. Presently he is the Co-Editor-in-Chief of Pattern Recognition, a member of the Advisory Board of Pattern Recognition Letters, and an Associate Editor of the International Journal of Pattern Recognition and Artificial Intelligence, Signal, video, and Image Processing, and Expert Systems with Applications. He was also an Associate Editor of the International Journal of Document Analysis and Recognition, the IEEE Trans. Pattern Analysis and Machine Intelligence, and Pattern Analysis and Applications.

A Fellow of the IEEE, IAPR, and the Academy of Sciences of the Royal Society of Canada, he has served several professional societies as President, Vice-President, or Governor. He is also the Founder and chair of several conference series including ICDAR, IWFHR, and VI. He was the General Chair of numerous international conferences, including the International Conference on Computer Processing of Chinese and Oriental Languages held in August 1988 in Toronto, International Workshop on Frontiers in Handwriting Recognition in April 1990 in Montreal, International Conference on Document Analysis and Recognition held held in Montreal in August 1995, and the International Conference on Pattern Recognition, held in Quebec City in August 2002.

Dr. Suen has given 150 seminars at major computer industries and various government and academic institutions around the world. He has been the principal investigator of 25 industrial/government research contracts, and has received many research grants from national and provincial funding agencies. He is a recipient of prestigious awards, including the ITAC/NSERC National Award from the Information Technology Association of Canada and the Natural Sciences and Engineering Research Council of Canada in 1992, the Concordia "Research Fellow" award in 1998, and the IAPR ICDAR Award in 2005.

Hubert Labelle, MD
Professor of Surgery
Motion Sciences Research Chair of CHU Sainte-Justine and University of Montreal
Montreal, Canada
Homepage
Title: Computer Assisted Surgery For Scoliotic Deformities Of The Spine : Perspectives Of A Spine Surgeon
Date: August 23, 2007

Abstract »

Over the past 3 decades, surgery for the treatment of scoliosis and other related spinal deformities in adolescents has evolved from a relatively simple to a progressively more complex procedure. Nowadays, the spinal deformity surgeon must acquire and master many new different surgical techniques such as minimally invasive surgery, video-assisted thoracoscopy, and thoracic or thoraco-abdominal instrumentations, which have been added to the more traditional method of posterior instrumentation and fusion of the spine. In addition, the recent proliferation of multi-rod hook and screw instrumentation systems designed to provide selective and 3D spinal correction with a minimal number of fusion levels, while still allowing the best possible correction, have led to a re-evaluation of many rules and guidelines. Finally, the introduction of new surgical manoeuvers such as rod rotation, cantilever, in situ rod contouring, and more recently of the direct apical vertebral derotation technique have also added to the challenge. As a result, the surgical decision making process has considerably increased in complexity, with many on-going controversies and debates over the choice of fusion levels, the proper guidelines for surgical correction, the use of thoracic pedicle screws and their insertion techniques as well as the risk of complications and the cost issues. In this presentation, the use of computer assisted surgery, its role in this on-going process and its evolution over the past decade from a research instrument towards a clinically relevant and useful tool will be reviewed, as seen from the point of view of a spinal deformity surgeon. In particular, the author�s experience with 3D reconstruction and imaging of spine, with trunk and rib cage deformities, with intra-operative tracking of the spine, trunk and surgical manoeuvres, and the role of computer simulation of surgical procedures in the decision-making process will be reviewed. With improvements in multi modal image fusion, the foreseen developments in computer assisted surgery towards minimally invasive and minimally irradiating procedures for the correction of spinal deformities will be discussed.

Bio »

Hubert Labelle was born in Montreal, Canada in 1952. He received a M.D.in 1976 and completed a residency in orthopaedics at University of Montreal in 1981, followed by a 2-year fellowship in paediatric orthopaedics at CHU Sainte-Justine Hospital in Montreal, Rancho Los Amigos Hospital in California and the A.I. Du Pont Institute in Delaware. Since 1982, he has been appointed in the department of surgery at University of Montreal and at CHU Ste-Justine where he is currently Professor of surgery and Titular of the Motion Sciences Research Chair of CHU Sainte-Justine and University of Montreal. His clinical work is focused on the evaluation and treatment of scoliotic deformities in children and adolescents. He is currently Chief of Orthopaedics, Chief of the musculoskeletal thematic research team, a multi-institutional and inter-disciplinary team, and Director of the 3-D Scoliosis Laboratory at CHU Sainte-Justine Research Center. Since 2002, he is also Head of MENTOR, a CIHR strategic research training programme on mobility and posture disorders which has contributed to the training of more than 50 researchers in this field. His research interests are concentrated on the 3-D evaluation and treatment of scoliotic deformities, with a particular emphasis on computer assisted surgery, 3-D design and evaluation of braces for the treatment of idiopathic scoliosis, and 3-D evaluation and simulation of surgery for scoliotic deformities.

Prabir Bhattacharya
Canada Research Chair in Information Systems
Professor, Concordia Inst. for Information Systems Engineering (CIISE)
Concordia University, Canada
Homepage
Title: A Framework for Image Retrieval using Machine Learning and Statistical Similarity Matching Techniques with Relevance Feedback
Date: August 24, 2007

Abstract »

The exponential growth of image data in various formats has created a practical need for the development of innovative tools for retrieving and analyzing information from large image databases. Many applications such as digital libraries and image search engines need to use efficient techniques to access digitized images based on their contents, commonly known as the content-based image retrieval (CBIR) method. While much research effort has been made on the development of CBIR systems, several issues still remain open. The early CBIR systems used low-level visual features without any semantic interpretation. In a database whose semantic description is reasonably well defined, it is possible to extract a set of low-level features to depict the semantic content of each image. In this talk, we shall discuss the techniques and issues related to the CBIR and then present our recent work based on machine learning and statistical pattern recognition, with a special emphasis on the retrieval of medical images. (This is a joint work with Mr. Mahmudur Rahman and Prof. Bipin Desai both of Concordia University.)

Bio »

Prabir Bhattacharya is a Full Professor at the Concordia University, Montreal, Canada where he holds a Canada Research Chair, Tier 1. He was earlier a Full Professor at the University of Nebraska-Lincoln, Department of Computer Science and Engineering, USA where he served during 1986-99. During 1999-2004, he worked as a Principal Scientist at the Panasonic Information Technologies Laboratory in Princeton, New Jersey. He received his Ph.D. from the University of Oxford, UK in 1979 and received his undergraduate education from the University of Delhi, India. He is a Fellow of the IEEE, the IAPR and the IMA. He is currently the Associate Editor-in-Chief of the IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics). Also, he is an associate editor of three other technical journals. He holds 3 US Patents, and has co-authored about 200 publications including 90 journal papers.


	Keynote Speakers Ching Suen Concordia Chair in AI & Pattern Recognition Director, CENPARMI Concordia University, Canada Homepage Title: Recognition of Cell Phone Face Images Date: August 22, 2007 Abstract » This paper presents (a) a survey on current techniques in the recognition of face images, (b) characteristics of cell phone face images, and (c) a new method of processing and verifying faces captured by cell phones. It describes various methods of detecting local face recognition such as eyes, mouth, and nose, focussing on point distribution model and active shape models. An example will be given on the recognition of cell phone face images. The key points of these faces have been extracted by an active shape model, and the feature vector has been constructed by applying a Gabor filter to the face images. The One Class Support Vector Machine (OC-SVM) has been used to classify the Gabor features. The database consists of 1000 face images built from dozens of SVM machines. This paper will be authored by Joanna Rokita, Adam Krzyzak, and Ching Suen CENPARMI - Centre for Pattern Recognition & Machine Intelligence Concordia University, Montreal, Quebec H3G 1M8, Canada Bio » Ching Y. Suen received an M.Sc.(Eng.) degree from the University of Hong Kong and a Ph.D. degree from the University of British Columbia, Canada. In 1972, he joined the Department of Computer Science at Concordia University where he became Professor in 1979 and served as Chairman from 1980 to 1984, and as Associate Dean for Research of the Faculty of Engineering and Computer Science from 1993 to 1997. He has guided/hosted 70 visiting scientists and professors, and supervised 65 doctoral and master's graduates. Currently he holds the distinguished Concordia Research Chair in Artificial Intelligence and Pattern Recognition, and is the Director of CENPARMI, the Centre for PR & MI. Prof. Suen is the author/editor of 11 books and more than 400 papers on subjects ranging from computer vision and handwriting recognition, to expert systems and computational linguistics. He is the founder of "The International Journal of Computer Processing of Oriental Languages" and served as its first Editor-in-Chief for 10 years. Presently he is the Co-Editor-in-Chief of Pattern Recognition, a member of the Advisory Board of Pattern Recognition Letters, and an Associate Editor of the International Journal of Pattern Recognition and Artificial Intelligence, Signal, video, and Image Processing, and Expert Systems with Applications. He was also an Associate Editor of the International Journal of Document Analysis and Recognition, the IEEE Trans. Pattern Analysis and Machine Intelligence, and Pattern Analysis and Applications. A Fellow of the IEEE, IAPR, and the Academy of Sciences of the Royal Society of Canada, he has served several professional societies as President, Vice-President, or Governor. He is also the Founder and chair of several conference series including ICDAR, IWFHR, and VI. He was the General Chair of numerous international conferences, including the International Conference on Computer Processing of Chinese and Oriental Languages held in August 1988 in Toronto, International Workshop on Frontiers in Handwriting Recognition in April 1990 in Montreal, International Conference on Document Analysis and Recognition held held in Montreal in August 1995, and the International Conference on Pattern Recognition, held in Quebec City in August 2002. Dr. Suen has given 150 seminars at major computer industries and various government and academic institutions around the world. He has been the principal investigator of 25 industrial/government research contracts, and has received many research grants from national and provincial funding agencies. He is a recipient of prestigious awards, including the ITAC/NSERC National Award from the Information Technology Association of Canada and the Natural Sciences and Engineering Research Council of Canada in 1992, the Concordia "Research Fellow" award in 1998, and the IAPR ICDAR Award in 2005. Hubert Labelle, MD Professor of Surgery Motion Sciences Research Chair of CHU Sainte-Justine and University of Montreal Montreal, Canada Homepage Title: Computer Assisted Surgery For Scoliotic Deformities Of The Spine : Perspectives Of A Spine Surgeon Date: August 23, 2007 Abstract » Over the past 3 decades, surgery for the treatment of scoliosis and other related spinal deformities in adolescents has evolved from a relatively simple to a progressively more complex procedure. Nowadays, the spinal deformity surgeon must acquire and master many new different surgical techniques such as minimally invasive surgery, video-assisted thoracoscopy, and thoracic or thoraco-abdominal instrumentations, which have been added to the more traditional method of posterior instrumentation and fusion of the spine. In addition, the recent proliferation of multi-rod hook and screw instrumentation systems designed to provide selective and 3D spinal correction with a minimal number of fusion levels, while still allowing the best possible correction, have led to a re-evaluation of many rules and guidelines. Finally, the introduction of new surgical manoeuvers such as rod rotation, cantilever, in situ rod contouring, and more recently of the direct apical vertebral derotation technique have also added to the challenge. As a result, the surgical decision making process has considerably increased in complexity, with many on-going controversies and debates over the choice of fusion levels, the proper guidelines for surgical correction, the use of thoracic pedicle screws and their insertion techniques as well as the risk of complications and the cost issues. In this presentation, the use of computer assisted surgery, its role in this on-going process and its evolution over the past decade from a research instrument towards a clinically relevant and useful tool will be reviewed, as seen from the point of view of a spinal deformity surgeon. In particular, the author�s experience with 3D reconstruction and imaging of spine, with trunk and rib cage deformities, with intra-operative tracking of the spine, trunk and surgical manoeuvres, and the role of computer simulation of surgical procedures in the decision-making process will be reviewed. With improvements in multi modal image fusion, the foreseen developments in computer assisted surgery towards minimally invasive and minimally irradiating procedures for the correction of spinal deformities will be discussed. Bio » Hubert Labelle was born in Montreal, Canada in 1952. He received a M.D.in 1976 and completed a residency in orthopaedics at University of Montreal in 1981, followed by a 2-year fellowship in paediatric orthopaedics at CHU Sainte-Justine Hospital in Montreal, Rancho Los Amigos Hospital in California and the A.I. Du Pont Institute in Delaware. Since 1982, he has been appointed in the department of surgery at University of Montreal and at CHU Ste-Justine where he is currently Professor of surgery and Titular of the Motion Sciences Research Chair of CHU Sainte-Justine and University of Montreal. His clinical work is focused on the evaluation and treatment of scoliotic deformities in children and adolescents. He is currently Chief of Orthopaedics, Chief of the musculoskeletal thematic research team, a multi-institutional and inter-disciplinary team, and Director of the 3-D Scoliosis Laboratory at CHU Sainte-Justine Research Center. Since 2002, he is also Head of MENTOR, a CIHR strategic research training programme on mobility and posture disorders which has contributed to the training of more than 50 researchers in this field. His research interests are concentrated on the 3-D evaluation and treatment of scoliotic deformities, with a particular emphasis on computer assisted surgery, 3-D design and evaluation of braces for the treatment of idiopathic scoliosis, and 3-D evaluation and simulation of surgery for scoliotic deformities. Prabir Bhattacharya Canada Research Chair in Information Systems Professor, Concordia Inst. for Information Systems Engineering (CIISE) Concordia University, Canada Homepage Title: A Framework for Image Retrieval using Machine Learning and Statistical Similarity Matching Techniques with Relevance Feedback Date: August 24, 2007 Abstract » The exponential growth of image data in various formats has created a practical need for the development of innovative tools for retrieving and analyzing information from large image databases. Many applications such as digital libraries and image search engines need to use efficient techniques to access digitized images based on their contents, commonly known as the content-based image retrieval (CBIR) method. While much research effort has been made on the development of CBIR systems, several issues still remain open. The early CBIR systems used low-level visual features without any semantic interpretation. In a database whose semantic description is reasonably well defined, it is possible to extract a set of low-level features to depict the semantic content of each image. In this talk, we shall discuss the techniques and issues related to the CBIR and then present our recent work based on machine learning and statistical pattern recognition, with a special emphasis on the retrieval of medical images. (This is a joint work with Mr. Mahmudur Rahman and Prof. Bipin Desai both of Concordia University.) Bio » Prabir Bhattacharya is a Full Professor at the Concordia University, Montreal, Canada where he holds a Canada Research Chair, Tier 1. He was earlier a Full Professor at the University of Nebraska-Lincoln, Department of Computer Science and Engineering, USA where he served during 1986-99. During 1999-2004, he worked as a Principal Scientist at the Panasonic Information Technologies Laboratory in Princeton, New Jersey. He received his Ph.D. from the University of Oxford, UK in 1979 and received his undergraduate education from the University of Delhi, India. He is a Fellow of the IEEE, the IAPR and the IMA. He is currently the Associate Editor-in-Chief of the IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics). Also, he is an associate editor of three other technical journals. He holds 3 US Patents, and has co-authored about 200 publications including 90 journal papers.
ICIAR - International Conference on Image Analysis and Recognition Send your comments to [email protected]