A.Rajalingam. Int. Journal of Engineering Research and Application www.ijera.com ISSN : 2248-9622, Vol. 7, Issue 9, ( Part -2) September 2017, pp.70-76 www.ijera.com DOI: 10.9790/9622-0709027076 70 | Page Optical Character Recognition Using Line and Character Segmentation * A.Rajalingam 1 , M.Ramkumar Prabhu 2 Department of Electronics & Communication Engineering 1 Professor, Shinas College of Technology, Sultanate of Oman 2 Professor, Apollo Priyadarshanam Inst. Of Technology, Chennai, India. Corresponding Author: A.Rajalingam ABSTRACT The digital image processing (DIP) has been employed in a number of areas, particularly for feature extraction and to obtain patterns of digital images. Recognition of characters is a novel problem, and although, currently there are widely-available digital image processing algorithms and implementations that are able to detect characters from images, selection of an appropriate technique that can straightforwardly acclimatize to diverse types of images, that are very specific or complex is very important. This paper presents a brief overview of digital image processing techniques such as image restoration, image enhancements, and feature extraction, a framework for processing images and aims at presenting an adaptable digital image processing method for recognition of characters in digital images. Keywords: Image processing, digital image processing, thresholding, morphological thinning, hough transform, character recognition, Digital Image Processing -------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: 24-08-2017 Date of acceptance: 09-09-2017 -------------------------------------------------------------------------------------------------------------------------------------- I. INTRODUCTION Imaging has undergone certain developments with the advancement of technology and science. The reason why an image can be digitized is to be transformed into computer memory storable or other forms media storage such as CD-ROM or hard disk. Digital image is a representation of a double- dimensional image as a limited set of digital values known as pixels or picture elements. The digitization procedure can be conducted through a scanner or video camera. Once an image is digitized, it can done using different image processing operations Digital image processing lays emphasis on two main tasks: amelioration of pictorial information for the purposes of human interpretation and processing of data image for storage, representation, and transmission for independent machine perception. The purpose of digital image processing is to find a delegacy of intensity distribution of any image and changing 3D images to 2D image values that is utilizable for quantitative morphology description and representation (Samantaray, Panda, & Pradhan, 2011, p.56). Digital image processing often engage many procedures such as formatting and correcting the data, digital enhancement to enhance an improved visual interpretation, or automated target classifications and features wholly by computer. For an individual to develop remote sensing imagery in a digital manner, the data has to be available and recorded in a digital form that is eligible for storage on a computer disk or tape. In addition, the other prerequisite for the processing of digital image is a computer system, at times known as image analysis system which has appropriate software and hardware to manufacture data. Several software systems available commercially have been created specifically for remote sensing image analysis and processing. There are different methods or techniques that have been part of the digital image processing procedures. Preprocessing, Image Enhancement, Image Transformation and Image Classification and Analysis are a good number of common image processing functions available in the analysis of image. Preprocessing involves the operations that are often required before to the main analysis of data and information extraction and are broadly grouped as geometric or radiometric corrections. Radiometric corrections incorporate correcting the data for sensor irregularities and undesirable sensor or atmospheric noise, as well as converting the data such that they precisely represent the emitted or reflected radiation measured by the sensor. Geometric corrections on the contrary, include amending the geometric distortions because of sensor-earth geometry variations, and rebirth of the data to actual world coordinates such as longitude and latitude on the surface of the earth (Cho, et al., 2012, p. 2).Image Enhancement involves modification of one or more components of the image to increase clarity and details through the visual analysis and interpretation. It looks also to modify the visual impact in a way that enhances the information content of the image as in Figure 1. RESEARCH ARTICLE OPEN ACCESS