Eigenpaxels and a neural-network approach to image classification

A expansion encoding approach to image classification is presented. Localized principal components or "eigenpaxels" are used as a set of basis functions to represent images. That is, principal-component analysis is applied locally rather than on the entire image. The "eigenpaxels" are statistically determined using a database of the images of interest. Classification based on visual similarity is achieved through the use of a single-layer error-correcting neural network. Expansion encoding and the technique of subsampling are key elements in the processing stages of the eigenpaxel algorithm. Tested using a database of frontal face images consisting of 40 individuals, the algorithm exhibits equivalent performance to other comparable but more cumbersome methods. In addition, the technique is shown to be robust to various types of image noise.

[1]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[2]  Alex Pentland,et al.  Beyond eigenfaces: probabilistic matching for face recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[3]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

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

[5]  Norman I. Badler,et al.  Three-dimensional representations for computer graphics and computer vision , 1978, SIGGRAPH.

[6]  David L. Waltz,et al.  Generating Semantic Descriptions From Drawings of Scenes With Shadows , 1972 .

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

[8]  Dennis Gabor,et al.  Theory of communication , 1946 .

[9]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[11]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[12]  Leslie S. Smith,et al.  The principal components of natural images , 1992 .

[13]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[14]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[15]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

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

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

[18]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[19]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[20]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[21]  James S. Albus,et al.  Brains, behavior, and robotics , 1981 .

[22]  D. P. W. Graham,et al.  «Move»: a neural network paradigm for robotic control , 1991 .