Segmentation of Broken and Isolated characters in Handwritten Gurumukhi Word using Neighboring pixel technique
Akashdeep Kaur, Paramjeet Singh, Shaveta Rani · Transactions on Networks and Communications · 2015
Character Segmentation of Handwritten Documents has been an active area of research and due to its diverse applicable environment; it continues to be a challenging research topic. In this paper, the focus is on offline segmentation of handwritten documents written in Gurumukhi Script. The desire to edit scanned text document forces the researchers to think about the optical character recognition (OCR). OCR is the process of recognizing a segmented part of the scanned image as a character. OCR process consists of three major sub processes - pre processing, segmentation and then recognition. Out of these three, the segmentation process is the most important phase of the overall OCR process. In this paper, algorithm is formulated to segment the scanned document image as a character that can be isolated or broken from within the given word. According to proposed algorithm, one part is extracting line from a document other part is extracting a word from the line. Segmentation part of the algorithm extracts characters from the extracted word. To segment the characters from a word, combination of two approaches which are Horizontal Profile Project and Vertical Profile Projection is used and will formulate a new algorithm which is Neighboring Pixel algorithm for touching characters in a word written in Gurumukhi script.