Multi-layered feedforward neural networks for image segmentation

Artificial neural network image segmentation techniques are examined. The biological inspired cortex transform is examined as a means to preprocess images for segmentation and classification. A generalized neural network formalism is presented as a means to produce common pattern recognition processing techniques in a single iterable element. Several feature reduction preprocessing techniques, based on feature saliency, Karhunen-Loeve transformation and identity networks are tested and compared. The generalized architecture is applied to a problem in image segmentation, a tracking of high-value fixed tactical targets. A generalized architecture for neural networks is developed based on the second order terms of the input vector. The relation between several common neural network paradigms is demonstrated using the generalized neural network. The architecture is demonstrated to allow implementation of many feedforward networks and several preprocessing techniques as well. Because of the limited resources and large feature vectors associated with classification problems, several methods are tested to limit the size of the input feature vector. A feature saliency metric, weight saliency, is developed to assign relative importance to the individual features. The saliency metric is shown to be significantly easier to compute than previous methods. Several neural network implementations of identity networks are tested as a means to reduce the size of the feature vectors presented to classification networks. Using the generalized approach, a scanning receptive field neural network is developed for image segmentation. The scanning window technique is used to segment sequential images of high value fixed targets (dams, bridges and power plants). The architecture is implemented as a tracking mechanism. The implementation resulted in an improved method for target identification and tracking, using neural networks as a front end.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[3]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[4]  Ray S. Snider.  A Proposed Model for Visual Information Processing in the Human Brain , 1967, Neurology.

[5]  A. Barron,et al.  Statistical properties of artificial neural networks , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[6]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[7]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[8]  Oscar Firschein,et al.  Readings in computer vision: issues, problems, principles, and paradigms , 1987 .

[9]  Donald H. Foley.  Considerations of sample and feature size , 1972, IEEE Trans. Inf. Theory.

[10]  R.W. Ehrich,et al.  Computer image processing and recognition , 1981, Proceedings of the IEEE.

[11]  Casimir C. Klimasauskas.  Neural nets tell why , 1991 .

[12]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[13]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[14]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[15]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[16]  Steven E Troxel.  Position, Scale, and Rotation Invariant Target Recognition Using Range Imagery. , 1987 .

[17]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[18]  Steven K. Rogers,et al.  EFFECTIVE NEURAL NETWORK MODELING IN C , 1991 .

[19]  Terrence J. Sejnowski,et al.  Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.

[20]  T. L. Reguianski.  The Air Force Institute of Technology , 1962 .

[21]  B. Julesz,et al.  Human factors and behavioral science: Textons, the fundamental elements in preattentive vision and perception of textures , 1983, The Bell System Technical Journal.

[22]  M. K. Fleming,et al.  Categorization of faces using unsupervised feature extraction , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[23]  Steven K. Rogers,et al.  Bayesian selection of important features for feedforward neural networks , 1993, Neurocomputing.

[24]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[25]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..