Handwritten Digit Recognition Using Neural Network Approaches and Feature Extraction Techniques: a Survey

In computer vision the most difficult task is to recognize the handwritten digit. Since the last decade the handwritten digit recognition is gaining more and more fame because of its potential range of applications like bank cheque analysis, recognizing postal addresses on postal cards, etc. Handwritten digit recognition plays a very vital role in day to day life, like in a form of recording of information and style of communication even with the addition of new emerging techniques. The performance of Handwritten digit recognition system is highly depend upon two things: First it depends on feature extraction techniques which is used to increase the performance of the system and improve the recognition rate and the second is the neural network approach which takes lots of training data and automatically infer the rule for matching it with the correct pattern. In this paper we have focused on different methods of handwritten digit recognition that uses both feature extraction techniques and neural network approaches and presented a comparative analysis while discussing pros and cons of each method.