INVARIANT BANGLA CHARACTER RECOGNITION USING A PROJECTION-SLICE SYNTHETIC-DISCRIMINANT-FUNCTION-BASED ALGORITHM

The projection-slice theorem has been used to create synthetic-discriminant-function based matched filters that are capable of discerning rotation and scale distortions. We propose to use the projectionslice algorithm for invariant Bangla character recognition that is capable of accommodating different handwriting and font-style distortions. The projection-slice algorithm is applied to training images in order to synthesize a composite image to represent each class. The opto-electronic fringe-adjusted joint transform correlator (JTC) technique is then used to correlate the test images with the composite images of each class. This technique is chosen for its superior performance to alternative JTCs and the feasibility of its implementation in the all-optical domain. Simulation results are furnished to prove the effectiveness of the proposed system.