Automated Off-Line Cursive Handwritten Words Recognition

The importance of the piece of paper cannot be ignored towards facilitating communication between people. People generally store important information by writing on paper for retrieving at a later stage. Paper is still a convenient and feasible way of storing data in the form of handwritten script or printed text. A huge amount of historical data is also written on papers. So, there is a great demand to digitize all these paper documents so that the people all over the world can access these important sources of knowledge. Many researchers are attempting to simulate intelligent behavior and mimic the human brain’s ability to read and recognize the handwritten or printed characters from the paper surface so that the computer can understand this script and process the data. For this purpose, the image of handwritten text is extracted, preprocessed and segmented into individual characters and are recognized by a neural network classifier. The automated processing of handwritten material optimizes the data processing speed as compared to manual processing and delivers very high recognition accuracy in least cost.