Image object classification using saccadic search, spatio-temporal pattern encoding and self-organisation

Abstract A method for extracting features from photographic images is investigated. The input image is through a saccadic search algorithm divided into a set of sub-images, segmented and coded by a spatio-temporal encoding engine. The input image is thus represented by a set of characteristic pattern signatures, well suited for classification by an unsupervised neural network. A strategy using multiple self-organising feature maps (SOM) in a hierarchical manner is used. With this approach, using a certain degree of user selection, a database of sub-images is grouped according to similarities in signature space.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Bart De Ketelaere,et al.  A hierarchical Self-Organizing Map for egg breakage classification , 1997 .

[3]  Vittorio Murino,et al.  Structured neural networks for pattern recognition , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[4]  Christopher B. Currie,et al.  Visual stability across saccades while viewing complex pictures. , 1995, Journal of experimental psychology. Human perception and performance.

[5]  Armando Freitas da Rocha,et al.  Neural Nets , 1992, Lecture Notes in Computer Science.

[6]  Clark S. Lindsey,et al.  Hybrid neural networks for automatic target recognition , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[7]  Sven Behnke,et al.  Competitive neural trees for pattern classification , 1998, IEEE Trans. Neural Networks.

[8]  C R Rao.  Geometry of circular vectors and pattern recognition of shape of a boundary. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[9]  J. Henderson,et al.  The effects of semantic consistency on eye movements during complex scene viewing , 1999 .

[10]  David Horn,et al.  Solitary Waves of Integrate-and-Fire Neural Fields , 1997, Neural Computation.

[11]  Wilson S. Geisler,et al.  IEEE TRANSACTIONS ON SYSTEMS , MAN , AND CYBERNETICS — PART A : SYSTEMS AND HUMANS , 2009 .

[12]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[13]  Jason M. Kinser.  Foveation by a pulse-coupled neural network , 1999, IEEE Trans. Neural Networks.

[14]  Jason M. Kinser,et al.  Image Processing using Pulse-Coupled Neural Networks , 1998, Perspectives in Neural Computing.

[15]  Ponnuthurai N. Suganthan.  Hierarchical overlapped SOM's for pattern classification , 1999, IEEE Trans. Neural Networks.

[16]  P H Schiller,et al.  Visual representations during saccadic eye movements. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Juyang Weng,et al.  Hierarchical Discriminant Analysis for Image Retrieval , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  J. L. Johnson.  Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images. , 1994, Applied optics.

[19]  Reinhard Eckhorn,et al.  Neural mechanisms of scene segmentation: recordings from the visual cortex suggest basic circuits for linking field models , 1999, IEEE Trans. Neural Networks.

[20]  Martin Kermit,et al.  Feature extraction from photographic images using a hybrid neural network , 1999, Other Conferences.