Generic Solution for Image Object Recognition Based on Vision Cognition Theory

Human vision system can understand images quickly and accurately, but it is impossible to design a generic computer vision system to challenge this task at present. The most important reason is that computer vision community is lack of effective collaborations with visual psychologists, because current object recognition systems use only a small subset of visual cognition theory. We argue that it is possible to put forward a generic solution for image object recognition if the whole vision cognition theory of different schools and different levels can be systematically integrated into an inherent computing framework from the perspective of computer science. In this paper, we construct a generic object recognition solution, which absorbs the pith of main schools of vision cognition theory. Some examples illustrate the feasibility and validity of this solution.

[1]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[2]  Matthew Brand,et al.  Physics-Based Visual Understanding , 1997, Comput. Vis. Image Underst..

[3]  Pietro Perona,et al.  Selective visual attention enables learning and recognition of multiple objects in cluttered scenes , 2005, Comput. Vis. Image Underst..

[4]  Xu De,et al.  Method for qualitatively evaluating CVIR algorithms based on human similarity judgments , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[5]  Laurent Itti,et al.  A Goal Oriented Attention Guidance Model , 2002, Biologically Motivated Computer Vision.

[6]  Martin D. Levine,et al.  Representing 3-D Objects in Range Images Using Geons , 1996, Comput. Vis. Image Underst..

[7]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[8]  Morshed U. Chowdhury,et al.  Image semantic classification by using SVM , 2003 .

[9]  Ramakant Nevatia,et al.  Automatic description of complex buildings from multiple images , 2004, Comput. Vis. Image Underst..

[10]  Seong-Whan Lee,et al.  Biologically Motivated Computer Vision , 2002, Lecture Notes in Computer Science.

[11]  Antonio Torralba,et al.  Top-down control of visual attention in object detection , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[12]  Sven J. Dickinson,et al.  Panel report: the potential of geons for generic 3-D object recognition , 1997, Image Vis. Comput..

[13]  Kim L. Boyer,et al.  Using Perceptual Inference Networks to Manage Vision Processes , 1995, Comput. Vis. Image Underst..

[14]  Kobus Barnard,et al.  Recognition as Translating Images into Text , 2003, IS&T/SPIE Electronic Imaging.

[15]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[16]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[17]  Weibin Liu,et al.  Superquadric-based geons recognition utilizing support vector machines , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[18]  H. Ridley.  Eye and Brain , 1973 .

[19]  Irving Biederman,et al.  Visual object recognition , 1993 .

[20]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[21]  James Ze Wang,et al.  Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Michael S. Lew,et al.  Principles of Visual Information Retrieval , 2001, Advances in Pattern Recognition.