Handwritten Marathi character (vowel) recognition

The work in this paper is deals with the recognition of handwritten Marathi vowels. Marathi is anIndo-Aryan language spoken by about 71 million people mainly in the Indian state of Maharashtra andneighbouring states. Marathi is also spoken in Israel and Mauritius. Marathi is thought to be a descendent ofMaharashtri, one of the Prakrit languages which developed from Sanskrit. This work is based on invariantmoments for recognition of isolated Marathi Handwritten Characters and their divisions. The proposedtechnique is independent of size, slant, orientation, translation and other variations in handwrittencharacters. Handwritten Marathi Characters/Numerals are more complex for recognition than correspondingEnglish characters due to many possible variations in order, number, direction and shape of the constituentstrokes. The work treats isolated Characters as an image of 40X40 pixel size. Seven invariant centralmoments of the image and two additional feature sets are evaluated. 10 samples of each number from 20different writers have been sampled and prepared a database has been made. Seven central invariantmoments are evaluated for each character and its parts by dividing it by two different ways. In all, there are14 features corresponding to each character. The Gaussian Distribution Function has been adopted forclassification. The average success rate of some vowels is compatible.