PsyCOP-a psychologically motivated connectionist system for object perception

A connectionist system has been designed for learning and simultaneous recognition of flat industrial objects (based an the concepts of conventional and structured connectionist computing) by integrating the psychological hypotheses with the generalized Hough transform technique. The psychological facts include the evidence of separation of two regions for identification ("what it is") and pose estimation ("where it is"). The system uses the mechanism of selective attention for initial hypotheses generation. A special two-stage training paradigm has been developed for learning the structural relationships between the features and objects and the importance values of the features with respect to the objects. The performance of the system has been demonstrated on real-life data both for single and mixed (overlapped) instances of object categories. The robustness of the system with respect to noise and false alarming has been theoretically investigated.

[1]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[3]  R. H. Phaf,et al.  SLAM: A connectionist model for attention in visual selection tasks , 1990, Cognitive Psychology.

[4]  D. LaBerge,et al.  Theory of attentional operations in shape identification. , 1989 .

[5]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[6]  Stephen Michael Kosslyn,et al.  Information representation in visual images , 1975, Cognitive Psychology.

[7]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[8]  C. A. Murthy,et al.  A connectionist model for category perception: theory and implementation , 1993, IEEE Trans. Neural Networks.

[9]  Daniel Sabbah,et al.  Computing with Connections in Visual Recognition of Origami Objects , 1988, Cogn. Sci..

[10]  Michael C. Mozer,et al.  Perception of multiple objects - a connectionist approach , 1991, Neural network modeling and connectionism.

[11]  Geoffrey E. Hinton.  A Parallel Computation that Assigns Canonical Object-Based Frames of Reference , 1981, IJCAI.

[12]  Walter Schneider,et al.  Controlled and automatic human information processing: II. Perceptual learning, automatic attending and a general theory. , 1977 .

[13]  Min-Hong Han,et al.  Identification of cornerpoints of two-dimensional images using a line search method , 1989, Pattern Recognit..

[14]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[15]  Kunihiko Fukushima,et al.  Recognition and segmentation of connected characters with selective attention , 1993, Neural Networks.

[16]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[17]  S. Kosslyn,et al.  A computational analysis of mental image generation: evidence from functional dissociations in split-brain patients. , 1985 .

[18]  Stephen Grossberg,et al.  Recognition and segmentation of connected characters with selective attention , 1994, Neural Networks.

[19]  Kunihiko Fukushima,et al.  Cognitron: A self-organizing multilayered neural network , 1975, Biological Cybernetics.

[20]  Glenn S. Himes,et al.  Automatic Target Recognition Using a Neocognitron , 1992, IEEE Trans. Knowl. Data Eng..

[21]  Leslie G. Ungerleider.  Two cortical visual systems , 1982 .

[22]  C. A. Murthy,et al.  A self-organizing network for mixed category perception , 1996, Neurocomputing.

[23]  Pascal Fua,et al.  Computational strategies for object recognition , 1992, CSUR.

[24]  Richard A. Volz,et al.  Recognizing Partially Occluded Parts , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[26]  J. Duncan,et al.  Visual search and stimulus similarity. , 1989, Psychological review.

[27]  Sankar K. Pal,et al.  X-tron: an incremental connectionist model for category perception , 1995, IEEE Trans. Neural Networks.

[28]  M. Mozer,et al.  On the Interaction of Selective Attention and Lexical Knowledge: A Connectionist Account of Neglect Dyslexia , 1990, Journal of Cognitive Neuroscience.

[29]  ANDREW M. WALLACE,et al.  A comparison of approaches to high-level image interpretation , 1988, Pattern Recognit..

[30]  Geoffrey E. Hinton.  Shape Representation in Parallel Systems , 1981, IJCAI.

[31]  C. Bundesen.  A theory of visual attention. , 1990, Psychological review.

[32]  Ashok Samal,et al.  Multiconstraint shape analysis , 1986, Image Vis. Comput..

[33]  J. Feldman.  Four frames suffice: A provisional model of vision and space , 1985, Behavioral and Brain Sciences.

[34]  Carla H. Lagorio,et al.  Psychology , 1929, Nature.

[35]  Dana H. Ballard,et al.  Parameter Nets , 1984, Artif. Intell..

[36]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[37]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[38]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  K. Fukushima.  Neural network model for selective attention in visual pattern recognition and associative recall. , 1987, Applied optics.