English Handwritten Character Recognition using Convolutional Neural Network (CNN)

Character recognition is one of the most important research fields of image processing and pattern recognition. Character recognition is generally known as Optical Character Recognition (OCR).OCR is the process of electronic translation of handwritten images or typewritten text into machine editable text. It becomes very difficult if there are lots of paper based information on companies and offices. Because they want to manage a huge volume of documents and records. Computers can work much faster and more efficiently than human. It is used to perform many of the tasks required for efficient document and content management. But computer knows only alphanumeric characters as ASCII code. So computer cannot distinguish character or a word from a scanned image. In order to use the computer for document management, it is required to retrieve alphanumeric information from a scanned image. There are so many methods which are currently used for OCR and are based on different languages. The existing method like Artificial Neural Network (ANN) based on English Handwritten character recognition needs the features to be extracted and also the performance level is low. So a Convolutional Neural Network (CNN) based English handwritten character recognition method is used. It's a deep machine learning method for which it doesn't want to extract the features and also a fast method for character recognition.