Online Handwritten Sanskrit Character Recognition Using Support Vector Classification

摘要

Handwritten recognition has been one of the active and challenging research areas in the field of image processing. In this Paper, we are going to analyses feature extraction technique to recognize online handwritten Sanskrit word using preprocessing, segmentation. However, most of the current work in these areas is limited to English and a few oriental languages. The lack of efficient solutions for Indic scripts and languages such as Sanskrit has disadvantaged information extraction from a large body of documents of cultural and historical importance. Here we use Freeman chain code (FCC) as the representation technique of an image character. Chain code gives the boundary of a character image in which the codes represents the direction of where is the location of the next pixel. Randomized algorithm is used to generate the FCC. After that, features vector is built. The criterion of features toinput the classification is the chain code that converted to various features. And segmentation is applied to evaluate the possible segmentation zone. Accordingly, several generations are performed to evaluate the individuals with maximum fitness value. Support vector machine (SVM) is chosen for the classification step.