Font and Size Identification in Telugu Printed Document

Telugu is the official language derived from ancient Brahmi script and also one of the oldest and popular languages of India, spoken by more than 66 million people, especially in South India. While a large amount of work has been developed for font and size identification of English and other languages, relatively not much work has been reported on the development of OCR system for Telugu text. Font and size identification of Indian scripts is much more complicated than other scripts because of the use of huge number of combination of characters and modifiers. Font and size identification is the pre-processing step in OCR systems. Hence Telugu font and size identification is an important area if interest in the development of Optical Character Recognition (OCR) system for Telugu script. Pre processing tasks considered here are conversion of gray scale image to binary image, image clearing, and segmentation of the text into line, separation of connected components. Zonal analysis is applied and then top zone components are identified and checked for the presence of tick mark. Aspect ratio and pixel ratio for component are calculated. Comparing these two parameters with the database we identify the font and size. Simulation studies were carried out using MATLAB with GUI for all the segmentation methods for given Telugu text and the results it observed were good enough for identification of different fonts and sizes in the given Telugu text.