Title :
Training-based SLM-realizable composite filter design
Author_Institution :
Sch. of Eng. & Eng. Technol., Pennsylvania State Univ., University Park, PA, USA
Abstract :
Majority-granted nonlinearity-based training for the synthesis of a composite filter is proposed. The motivation is the limited modulation capability of the spatial light modulator (SLM) which is incorporated as a design constraint in the form of a simple thresholding scheme. The technique is simple, and less computationally extensive nevertheless resulting in a robust enough SLM-realizable distortion-invariant correlator. Simulation results are provided for the case of rotation invariant character recognition, which shows better correlation discrimination and robust recognition for a range of distorted characters
Keywords :
convolution; learning (artificial intelligence); nonlinear filters; optical character recognition; optical correlation; optimisation; simulation; spatial filters; spatial light modulators; SLM-realizable filter; composite filter design; correlation based optical pattern recognition; correlation discrimination; design constraint; distorted characters; filter synthesis; invariant filter performance; majority-granted nonlinearity-based training; phase only filter; robust distortion-invariant correlator; robust recognition; rotation invariant character recognition; simple thresholding scheme; simulation; training-based design; Character recognition; Computational modeling; Correlators; Design engineering; Educational institutions; Fourier transforms; Matched filters; Optical modulation; Phase distortion; Robustness;
Conference_Titel :
Aerospace and Electronics Conference, 1997. NAECON 1997., Proceedings of the IEEE 1997 National
Conference_Location :
Dayton, OH
Print_ISBN :
0-7803-3725-5
DOI :
10.1109/NAECON.1997.622729
