This paper describes how the Bangla characters are processed, trained and then recognized with the use of a neural network. The size and the font used for the characters are similar in both training and classification of the network. The images are first converted into grayscale and then to binary images. These images are then scaled to fit a pre-defined area. By extracting the characteristics points we get the feature vectors, which is simply a series of 0s and 1s of fixed length. Finally, an Artificial Neural Network is chosen for the training and classification process. It has been noticed that recognition decreases due to presence of touching characters in the text. So recognition is done here with isolated printed characters.
展开▼
