Shape Code Based Lexicon Reduction for Offline Handwritten Word Recognition

A novel method to reduce the lexicon size in handwritten word recognition is proposed in this paper. Due to large lexica, the computational cost of current word recognisers is often too high for practical applications. The proposed lexicon reduction method is based on character shape codes. We examine four different shape code mappings based on machine printed character font, on handprint, and on cursive handwriting. Experimental evaluation shows that the proposed method can reduce the computational effort while keeping the recognition rate high.