A New Approach to Bangla Text Extraction and Recognition From Textual Image

This paper presents a new approach to segment and recognize Printed Bangla Text using Characteristic functions and Hamming network. The main difficulties in printed Bangla text recognition are the separation of lines, words and individual characters. In this paper, a new algorithm has been proposed to detect and separate text lines, words and characters from printed Bangla text. The algorithm uses a set of characteristic functions for segmenting upper portion of some characters and characters that come under the Base line. It also uses a combination of Flood-fill and Boundary-fill algorithm for segmenting some characters that cannot be segmented using traditional approach. Hamming network is used for recognition scheme. Recognition is done for both isolated and continuous size independent printed characters.