Tutorial 1:

Title: Face Recognition

Tutor:

Stan Z. Li
Professor
Institute of Automation, Chinese Academy of Sciences,PR China

Stan Z. Li received his B.Eng from Hunan University, China, M.Eng from National University of Defense Technology, China, and PhD degree from Surrey University, UK. He is currently a professor and the director of Center for Biometrics and Security Research (CBSR), Institute of Automation, Chinese Academy of Sciences (CASIA). His research interest includes pattern recognition and machine learning, image and vision processing, face recognition, biometrics, and intelligent video surveillance. He has published over 200 papers in international journals and conferences, and authored and edited 8 books. He is currently an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence and acted as the editor-in-chief for the Encyclopedia of Biometrics (Springer Reference Work, 2009). He was elevated to IEEE Fellow for his contributions to the fields of face recognition, pattern recognition and computer vision.

 

Abstract of the Tutorial:

Face is one of the biometrics that has received intense research studies in the past decades. Significant progress has been made in the detection and recognition of it and the successes lead to many real-life applications using face technology. This tutorial focuses on the recognition of faces. It covers the prominent influential approaches and methods developed by researchers. Hence, it provides a good opportunity to graduate students and researchers to gain up-to-date knowledge in state-of-the-art this area from this tutorial, including the patented near-infra-red face technology. The tutorial will also cover some applications of face recognition such as the face verification in the Beijing Olympic Games, access control in Shanghai Expo, and auto-gates at Shen Zhen – Hong Kong Border Crossing. Hence, vision practitioners in industry can also benefited from this timely tutorial. The tutorial will also include several demo videos to how the methods work.

 

Outlines of the tutorial:

1. Introduction of face recognition
1.1 Subspace Analysis approach in face recognition
1.2 Linear Methods
1.3 Nonlinear Methods
1.4 Face Grand Challenges from Subspace Viewpoint

2. Face Analysis Methods
2.1 Face detection
2.2 Face Alignment
2.3 Face Recognition

3. Face Recognition Using Near Infrared Images

4. Heterogeneous Face Recognition

5. Applications

 

Tutorial 2:

Title: Perceptual Visual Manipulations: From Modules to Systems

Tutor:

Weisi Lin
Associate Professor
School of Computer Engineering, Nanyang Technological University, Singapore

Weisi Lin graduated from Zhongshan University, China with B.Sc and M.Sc in 1982 and 1985, respectively, and from King’s College, London University, UK with Ph.D in 1992. He taught and researched in Zhongshan University, Shantou University (China), Bath University (UK), National University of Singapore, Institute of Microelectronics (Singapore), and Institute for Infocomm Research (Singapore). He has been the project leader of 14 successfully-delivered projects (mostly for industries) in digital multimedia technology development since 1997. He also served as the Lab Head of Visual Processing and the Active Department Manager in Institute for Infocomm Research. Currently, he is an Associate Professor in School of Computer Engineering, Nanyang Technological University in Singapore. His areas of expertise include image processing, video and audio compression, perceptual modelling, computer vision, and multimedia communication. He is a Chartered Engineer, and a fellow of the IET. He currently serves on the editorial board of Journal of Visual Communication and Image Representation, four IEEE Technical Committees, and Technical Program Committees of a number of international conferences. He believes that good theory is practical, and keeps a good balance between academic research and industrial development.

 

Abstract of the Tutorial:

Since the human visual system (HVS) is the ultimate receiver and appreciator for the majority of processed images and video, it would be better to use a perceptually plausible criterion in the system design and optimization. After million-years of evolution, the HVS develops unique characteristics, which can be turned into the advantages for our designs. To make the machine perceive as the HVS does can result in resource savings (for instance, bandwidth, memory space, computing power) and performance enhancement (such as the resultant visual quality, and new functionalities). Significant research effort has been made toward modelling the HVS’ picture quality evaluation mechanism during the past decade, and to apply the resultant models to various situations.

In this tutorial, we will first introduce the problems under attack, and the relevant physiological/psychological knowledge. Afterward, we will present the two major parts of this tutorial. In the first mart part, the basic computational modules are to be discussed. These include the models for signal decomposition, Just-noticeable Difference (JND), visual attention, and common artifact detection. In the second major part, different perceptually-driven techniques will be presented for picture quality evaluation, signal compression, enhancement, transmission, and computer graphics. Since such technology has started to find applications in industries (although it is still in its infancy of development), we will discuss some examples of early industrial deployment.

This tutorial aims at providing a systematic, comprehensive and up-to-date overview in perception-based processing for images and video. It can also provide a practical user’s guide to the various relevant techniques (and those well-cited works to be highlighted), since all approaches are to be presented with clear classification, and careful comparison/comments whenever possible, based upon our understanding and experience in the said areas (in both academic and industrial aspects).

 

Outlines of the tutorial:

1. Introduction
1.1 Difficulties of traditional metrics/criteria/measures
1.2 Relevant physiological phenomena
1.3 Related psychophysical experiments

2. Basic Computing Modules Based on Psychophysical Findings
2.1 Signal decomposition
2.1.1 Temporal filtering
2.1.2 Spatial filtering
2.1.3 Gain Control Model
2.2 Just-noticeable Difference (JND)
2.2.1 Affecting factors
2.2.2 General Formulation
2.2.3 Pixel domain models
2.2.4 Subbands models
2.2.4.1 DCT
2.2.4.2 DWT
2.2.4.3 Others
2.2.5 Conversion between domains
2.2.6 Model evaluation and comparisons
2.3 Visual Attention
2.3.1 Feature derivation
2.3.2 Cognitive factors
2.3.3 Influence from speech/audio
2.3.4 Integration of stimuli
2.3.5 Modulation for JND
2.4 Common Artifact Detection
2.4.1 Blockiness
2.4.2 Blurring

3. Perceptual Visual Processing
3.1 Visual Quality Metrics
3.2 Video Compression
3.2.1 Improved compressibility
3.2.2 Motion Estimation
3.2.3 Quantization
3.2.4 Foveation-based coding
3.2.5 Inter-frame replenishment
3.3 Image Edge Enhancement
3.4 Image Rendering in Computer Graphics
3.4.1 Illumination Calculation
3.4.2 Real-time level-of-detail-based rendering
3.5 Case Studies for Industrial Deployment
3.6.1 JNDmetrixTM
3.6.2 Quality Monitoring in Manufacturing Environment
3.6.3 Rate Control for Videophone

4. Concluding Remarks and Possible Future Work
4.1 Modelling Advancement
4.2 Extension of Applications

©Copyright 2009-2010 PSIVT 2010