CSM-autossociators combination for degraded machine printed character recognition

This paper presents an OCR method that combines the complementary similarity measure (CSM) method with a set of autossociators for degraded character recognition. In the serial combination, the first classifier must achieve lower errors and be very well suited for rejection, whereas the second classifier must allow only low errors and rejects. We introduce a rejection criterion mode used as a quality measurement of the degraded character which makes the CSM-based classifier very powerful and very well suited for rejection. We report experimental results for a comparison of three methods: the CSM method, the autoassociator-based classifier and the proposed combined architecture. Experimental results show an achievement of 99.59% of recognition rate on poor quality bank check characters, which confirm that the proposed approach can be successfully used for effective degraded printed character recognition.