Modified-hybrid optical neural network filter for multiple object recognition within cluttered scenes

Motivated by the non-linear interpolation and generalization abilities of the hybrid optical neural network filter between the reference and non-reference images of the true-class object we designed the modifiedhybrid optical neural network filter. We applied an optical mask to the hybrid optical neural network's filter input. The mask was built with the constant weight connections of a randomly chosen image included in the training set. The resulted design of the modified-hybrid optical neural network filter is optimized for performing best in cluttered scenes of the true-class object. Due to the shift invariance properties inherited by its correlator unit the filter can accommodate multiple objects of the same class to be detected within an input cluttered image. Additionally, the architecture of the neural network unit of the general hybrid optical neural network filter allows the recognition of multiple objects of different classes within the input cluttered image by modifying the output layer of the unit. We test the modified-hybrid optical neural network filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. The filter is shown to exhibit with a single pass over the input data simultaneously out-of-plane rotation, shift invariance and good clutter tolerance. It is able to successfully detect and classify correctly the true-class objects within background clutter for which there has been no previous training.

[1]  JEFFREY WOOD,et al.  Invariant pattern recognition: A review , 1996, Pattern Recognit..

[2]  Philip Birch,et al.  Object recognition within cluttered scenes employing a hybrid optical neural network filter , 2004 .

[3]  B. Kumar,et al.  Generalized synthetic discriminant functions , 1988 .

[4]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

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

[6]  B V Kumar,et al.  Tutorial survey of composite filter designs for optical correlators. , 1992, Applied optics.

[7]  Martin T. Hagan,et al.  Neural network design , 1995 .

[8]  P. Réfrégier.  Filter design for optical pattern recognition: multicriteria optimization approach. , 1990, Optics letters.

[9]  H Toyoda,et al.  Adaptive optical processing system with optical associative memory. , 1993, Applied optics.

[10]  Fred Joseph Gruenberger,et al.  Computing: An Introduction , 1969 .

[11]  Philip Birch,et al.  A nonlinear training set superposition filter derived by neural network training methods for implementation in a shift-invariant optical correlator , 2003, SPIE Defense + Commercial Sensing.

[12]  B. V. Vijaya Kumar,et al.  Minimum-variance synthetic discriminant functions , 1986 .

[13]  Philip Birch,et al.  An investigation of the non-linear properties of correlation filter synthesis and neural network design , 2003 .

[14]  B. Krauskopf,et al.  Proc of SPIE , 2003 .

[15]  Ioannis Kypraios,et al.  Performance assessment of the modified-hybrid optical neural network filter. , 2008, Applied optics.

[16]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[17]  A. B. Vander Lugt,et al.  Signal detection by complex spatial filtering , 1964, IEEE Trans. Inf. Theory.

[18]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[19]  B. Widrow,et al.  The truck backer-upper: an example of self-learning in neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[20]  B. Kumar,et al.  Performance measures for correlation filters. , 1990, Applied optics.

[21]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .