3C vision : cues, contexts and channels

The exponential explosion of images and videos concerns everybody's common life, since this media is now present everywhere and in all human activities. Scientists, artists and engineers, in any field, need to be aware of the basic mechanisms that allow them to understand how images are essentially information carriers. Images bear a strong evocative power because their perception quickly brings into mind a number of related pictorial contents of past experiences and even of abstract concepts like pleasure, attraction or aversion.This book analyzes the visual hints, thanks to which images are generally interpreted, processed and exploited both by humans and computer programs.

Author Notes

Virginio Cantoni received the Laurea (cum laude) in Electronic Engineering in 1972 from Pavia University, Italy. He was a researcher of the Italian National Research Council from 1975 to 1983, and is presently a Full Professor of Computer Programming at Pavia University. From 1989 to 1995 Cantoni was Director of the Deparment of Computer Engineering, and from 1985 to 1990, he was the President of the Italian Group of the International Association for Pattern Recognition. He has been a Visiting Professor at Rutgers University, and has been Invited Professor at the Paris XI University. Levialdi is a Fellow of the IAPR and a senior member of IEEE.

Dr Stefano Levialdi, IEEE Life Fellow, has published 300 papers on image processing, image communication and, in these last years, his research has focused on Human/Computer Interaction (visual languages and usability). He is Full Professor of Computer Science at Sapienza, Rome University since 1981. He won the Chair of Excelence at Carlos III University in Madrid. He has organized, chaired and contributed to over 50 International meetings. He is the Director of LUA (Laboratory of Usability and Accessibility at Sapienza). He is now retired, but works for the Elsevier Journal (JVLC) and reviews national research projects. His email is: stefano.levialdi@gmail.com

Foreword	p. ix
Preface	p. xi
Acknowledgments	p. xv
1 Natural and Artificial Vision	p. 1
Natural Vision	p. 3
Artificial Vision	p. 4
Destructuring Images	p. 5
Structuring Images	p. 6
The V-Schema	p. 7
Images as Information Carriers	p. 8
Dissecting Images	p. 9
Artificial Vision Strategies	p. 10
Refining	p. 11
Scanning	p. 12
Focusing	p. 14
Tracking	p. 15
Hypothesis Testing	p. 15
Implementing on the Fly	p. 16
Conclusions	p. 16
2 Visual Cues	p. 19
The Human Headway	p. 19
Image Computer-Processing Tracks	p. 20
The Photometric Track	p. 21
Local Rendering	p. 21
Photometric Analysis	p. 25
Image Synthesis Following the Phong's Model	p. 27
Global Rendering	p. 27
Chromatic Clues	p. 33
The Morphological Track	p. 44
Shape Representation	p. 46
Shape Extraction	p. 62
Region Extraction	p. 71
The Spatial Track	p. 77
Space Modeling	p. 77
Space Extraction	p. 88
Decision Methods	p. 99
Statistical Decision	p. 100
Structural Decision	p. 101
Semantic Decision	p. 104
Conclusion	p. 105
3 The Role of Contexts	p. 115
Contexts According to Artists	p. 115
Direct Retrieval	p. 116
Recognition-Based Retrieval	p. 116
Search-Based Retrieval	p. 117
Context in Natural and Artificial Vision	p. 119
An Operative Definition of Context and Events	p. 121
The Perception and Action Framework	p. 123
The Biological Solution	p. 123
The Multiresolution Artificial Approach	p. 124
A Common Paradigm for Biological and Artificial Vision	p. 125
Direct Retrieval	p. 128
The Biological Visual Search	p. 129
The Artificial Visual Search	p. 132
Recognition-Based Retrieval	p. 134
The Biological Visual Classification	p. 134
The Computer Vision Solution	p. 137
Search-Based Retrieval	p. 146
Biological Context-Bound Interpretation	p. 146
The Automatic Behavior Analysis Track	p. 147
Contexts and New Technologies	p. 153
Toward Multimedia: Image Retrieval via Context	p. 153
Cooperative Data Analysis	p. 164
4 Channeling the Information	p. 177
Filling the Channels	p. 177
Multimedia Exploitation	p. 179
Icons and Metaphors	p. 183
Content Structure	p. 183
Social Interaction	p. 184
Role Rendering	p. 184
Multimedia Exploitation	p. 185
Seeing Through the Web	p. 186
Looking with the Web	p. 187
Ambient Intelligence	p. 192
Augmented Reality	p. 194
Pictorial Indexing	p. 195
Annotation	p. 197
Multimedia Communication	p. 199
Icons and Metaphors	p. 201
Current Icons	p. 203
The Blending Approach	p. 204
Structuring the Content	p. 206
Adding a New Channel	p. 206
Adding Pictures	p. 207
Representation Grammars	p. 208
Media Organization	p. 210
Social Interaction	p. 211
Usability	p. 212
Accessibility	p. 219
Cognitive Networks	p. 223
Role Definition for Virtual Realism	p. 224
Reality and Illusion	p. 224
Games	p. 227
Animation	p. 229
Cyberspace	p. 231
Final Remarks and Conclusions	p. 232

Available:*

On Order

Summary

Summary

Author Notes

Table of Contents