Evaluation of optical character recognition algorithms and feature extraction techniques

Optical character recognition or OCR becomes necessary first step for all applications that consider typewritten or handwritten manuscripts as input. We need to train our classifier in case we are considering to use data mining techniques for such purposes. There are several established generic classification techniques that can be used together with feature extraction mechanisms but it is important to know which of them do better under which circumstances. We evaluate three approaches for OCR from handwritten manuscripts and we study their results. We consider a case study where we need to identify cases with probability of dyslexia.