Multilingual Online Handwriting Recognition System: An Android App

Abstract

On-line handwriting recognition means recognizing the user's handwriting as the user is writing the character/stroke, i.e. the recognition is concurrent to the writing process. This paper describes a Multilingual Online handwriting recognition system in Android using SFAM Artificial Neural Network Technique. The app allows the user to select any of the target languages supported. The handwriting sequences are collected by the digitization of the pen/stylus movements as an array of x, y coordinates which is called a stroke. The structural and directional information are extracted from each character/stroke. The extracted features as a feature vector are passed as input to a SFAM artificial neural network (ANN) classifier. The SFAM classifier then performs a comparison of the input data with the trained data and finds the nearest prototype from the database that 'resonates' with the input pattern. The labels/recognized characters are assigned their corresponding Unicode code points and displayed using appropriate fonts.