HANDWRITTEN CHARACTER RECOGNITION USING MACHINE LEARNING

The aim of this work is to review existing methods for the handwritten digit recognition problem using machine learning algorithms and implement one of them for a user-friendly Android application. The main tasks the application provides a solution for are handwriting recognition based on touch input, handwriting recognition from live camera frames or a picture file, learning new characters, and learning interactively based on user's feedback. The recognition model we have chosen is a Support Vector Machines (SVMs) and Nearest Neighbor (NN) techniques especially because of its high performance on nonlinearly separable problems.