An improved discriminative region selection methodology for online handwriting recognition

The task of online handwriting recognition (HR) becomes often challenging due to the presence of confusing characters which are separable by a small region. To address this problem, we propose a “discriminative region (DR) selection” technique which highlights the discriminative region that distinguishes one character from another similar character. The existing DR selection approach for online handwriting often finds spurious DR when the intra-class shape variations become higher than the distinction between DRs of the two characters. The proposed technique which is an improved version of the existing approach can minimize the effect of high intra-class variations and results in robust DR selection. In addition, we propose an online HR system enabling DR-based processing in a single-stage classification framework. The use of hidden Markov model and support vector machine classifiers is explored to develop the HR system. The efficacy of the proposals is shown for character and word recognition tasks and evaluated on three databases: the locally collected Assamese character database, UNIPEN English character database and UNIPEN ICROW-03 word database. The recognition results are promising over the reported works.