Online handwritten malayalam character recognition using LIBSVM in matlab

This paper proposes an experimental technique to find the Malayalam Handwritten Character Recognition using support vector machines (SVM). Malayalam is a south indian language originated from brahmi script spoken about 35 million people especially in Kerala and Lakshadweep islands. It has the largest number of alphabets of 128 characters among indian languages. Online Malayalam Handwritten Character Recognition has been studied from the past several years, demands to replace a large keyboard because of huge alphabet size for texting applications and easy convenience of writing in our own style, signature verifications etc. Real time (x,y) coordinates per stroke are acquired and preprocessed. Directional and Curvature features are extracted and trained in LIBSVM, a tool for SVM Classifiers. Testing alphabet is given online to the trained SVM network and the recognized label is displayed in Notepad. Experiments are done for handwritten basic vowel alphabets (8) in Malayalam. Recognition speed of a single stroke is attained 0.52 secs.