In the proposed model for OCR, a neural network and digital signal processor classifier are used. The neural network
being used is a multi-layer perceptron network with backpropagation for learning. The input is the pixel data from the images.
Our system is able to do for computer typed and hand written, it can detect alpha numeric, figures, and special Symbols. Also to
add onto the system a figure scan and labelling solution is also provided. The three phases in the proposed model are
classification phase, training phase and recognition phase. Further to this our proposed system is robust to train new characters,
shapes and signs. A multi-level UI design is developed and interlinked. Images can be either taken from data set or live i.e.
captured from a sub cam or a mobile and fed to the system.
