IJSRST1738150 | Received : 25 Nov 2017 | Accepted : 18 Dec 2017 | November-December-2017 [(3)8: 930-937] © 2017 IJSRST | Volume 3 | Issue 8 | Print ISSN: 2395-6011 | Online ISSN: 2395-602X Themed Section: Science and Technology 962 Analysis of Different Recognition Technique Classification and their Accuracy Measure over Odia Script-A Review Rajat Ketan Sahu * , Anita Minz, Sagarika Mishra, Chandrasekhar Panda Department of Computer Science and Application, Sambalpur University, Jyoti Vihar, Burla, Odisha, India rajat.keten.sahu@gmail.com, dr.chandrasekharpanda@gmail.com ABSTRACT This paper presents a literature review on character recognition techniques. (OCR) Optical Character Recognition frameworks are able to identify varieties of text styles and printed characters. This means that by scanning a document the device is able to essentially „read‟ the content. Character identification is a requesting specialization of pattern recognition, machine learning, and advance image processing. Various work has been done as such far for independent Indian language like Hindi, Urdu, Gujarati, Punjabi and onward. The latest research in this area has been capable to grow some new methodologies to overcome the difficulty of Odia writing style. Be that as it may, narrow exploration has been done over on odia content. Thus far various techniques are projected for segmentation, feature extraction, classification, and recognition tasks of Odia characters. This paper tries to review, their relative strength and weakness unit layout done by various research worker over on Odia content in last few years. The basic objective of this paperwork is to nearby present an overview of different existing methods that have been developed to recognize Odia character throughout last decade. The paper may be a concern the individuals who are interested to work in the fields of acknowledgment of Odia script. Keywords : Optical Character Recognition (OCR), Odia Script, Classification, Recognition. I. INTRODUCTION Optical character recognition (OCR) deal with the technique of converting or changing over the handwritten text or printed content into a machine representation, that is understood by the machines for easy editing and looking. The greatest trail inside the field of image processing is to acknowledged the documents both in machine printed and handwritten structure [1]. Optical Character Recognition is a type of document image analysis where a scanned digital image that involves either machine printed or handwritten script input into an OCR software engine converts it into an editable machine readable digital text format[2].Development of OCR for different Indian languages is an active community of research work in today‟s era. We are creating and aim to develop the Hand written Character recognition framework for Odia conversation, which is the official language of Odisha.A part of research, is done on the printed Odia script, however a little mass of work has been done on the handwritten Odia content for recognition. Partition of handwritten or printed text into lines, words, and characters is one of the prime footsteps in the handwritten text recognition outlook. The text of hand written can be difficult to recognize due to variation in font sizes, type of noises, color, contrast, alignment, and background information. This kind of modification is difficult to identify the word in the document while writing [3]. Since handwritten text will vary on the user‟s skill, orientation and manner of the writing method. An in-depth study of Odia character recognition, outlining existing ways and their drawbacks have been carried out in this paper and future research direction in this field has been suggested. The various steps of character recognition such as image acquisition, preprocessing, segmentation, feature extraction, and post-processing. There are collections of application domain where, OCR can help. Major areas are represented below: 1. Protect past records in electronic format. 2. Save document pictures inside limited space.