OPTICAL CHARACTER RECOGNIZERMr. N. Bhaswanth1, N. Sai Gayathri2, G. Praveen Kumar3, K. Sai Sindhuja4Department of Information Technology,B. Tech, Information Technology,Institute of Aeronautical Engineering, Dundigal.
ABSTRACTRecent years have seen associate degree increasing interest in good phones, their harnessing usage in day to day life. The OCR (Optical Character Recognizer) technology integrated with humanoid apps will convert the scanned image of a text page to a word file instantly while not the effort of typewriting the complete content down again. The projected project aims to make associate degree OCR (Optical Character Recognizer) application for humanoid based smart phones. Associate degree OCR application is employed to find text presenting a picture. It uses algorithms which may be trained to acknowledge lines in a picture as text and converts the scanned page into PDF during which the extracted text are going to be hold on and may be altered. This application is accustomed forestall the time intense task of manually typewriting in letters, the text obtained after scanning by victimization this application is derived to a brief storage in an exceedingly device. Security is provided to the user’s storage that is maintained by not giving access to the unauthorized users. The applying implements a forked version of Google’s cloud vision API that contains the rule from which the text is generated. I.INTRODUCTIONMobile applications grew in but 20 years to realize the standing of the biggest data repository in human history. By providing economical, fast, consistent and authentic tools within the kind of web and mobile applications, data technology is penetrating human life and is enjoying a crucial role in dynamic lives of such a lot of individuals across the world. Nowadays several ancient industrial companies area unit moving towards utilizing data Technology as well as mobile applications. Mobile applications run banking transactions, traffic, and hospital room instrumentation. Nowadays, there’s a massive demand in storing any data on the market on papers like books or newspapers in mobile phones. There’s associate degree existing thanks to store data by scanning the specified text, however it’ll be keep as a picture that will not facilitate for additional process. For example, if we have a tendency to store scanned text pictures, we won’t browse the text word by word, or line by line. The text in these scanned pictures cannot be reused unless we have a tendency to rewrite the total content by ourselves. For this reason, we’d like associate degree Optical Character Recognizer (OCR).Scanned documents can allow us to archive stacks of paper into folder, absorbing so much less area and being infinitely easier to prepare, move, and copy. By default, they are very little over an image of our document—and if we wish to seek out data within them, weought to open all and browse it for ourselves. Or, we have a tendency to might let our device do the work for United States of America, by turning your image into text and rental United States of America search through our scanned documents as simply as we have a tendency to search through the other documents. That is what OCR (Optical Character Recognizer) will. It uses our computer’s smarts to acknowledge letter shapes in a picture or scanned document, and switch them into digital text we will copy and edit as required.II.LITERATURE STUDY”Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition”1 in this paper, the characters are recognized from the image that is already taken by the mobile’s camera. And those characters were passed for further processing.”Optical Character Recognition Technique Algorithms” 2 in this paper, they presented a new neural network (NN) based method for optical character recognition (OCR).”The Optical Capture Recognition” 3 this project has developed an Optical Capture Recognition (OCR) for Android based mobile devices. Scanned text documents, pictures stored in mobile phones having Android as operating system.”High accuracy optical character recognition algorithms using learning array of ANN”4 the performance of the current OCR illustrates and explains the actual errors and imaging defects in recognition with illustrated examples. This paper aims to create an application interface for OCR using artificial neural network as a back end. “Text recognition from images” 5 text recognition in images is a research area which attempts to develop a computer system with the ability to automatically read the text from imagesIII. PROPOSED METHODOLOGYA new application that may be useful for users. This application will be accustomed forestall the time intense task of manually typewriting in letters. The user of the applying scans the text needed exploitation the device camera and stores the desired text once detected. The main advantage of this application is that overcomes the menial task of taking footage and awaiting results. Provides a period of time answer to look for text. Provides answer to the drawbacks of existing system that cannot store the detected text.Figure 1: Schematic overview of the proposed framework.The following context diagram of OCR can be described as follows:1. User-OCR Application: it’s one to one relationship as a result of just one user interacts with the applying at a time. 2. OCR Application-Image: the applying is in a position to method one image at a time. 3. User-Image: The user will either take an image or select one from the phone directory. 4. Image-Text: The image should contain text. 5. Text-Words: The text will contain several words. 6. Words-Characters: Every word will have any range of English Alphabet’s characters. 7. User-Text: The user will copy, paste, or choose the full text or simply an area of it.After the method is completed the results are displayed. Figure 3. Context diagram. IV. CONCLUSIONThe automatic entry of information victimization OCR is one amongst the foremost engaging and labour reducing technology. The popularity of recent font characters by system is extremely simple and fast. We will be able to edit info of the data of documents a lot of handily and that we can reprocess the emended information as and once needed. The extension to computer code apart from piece of writing and looking out is topic for future works.V. ACKNOWLEDGEMENTWe would like to express our gratitude to all the people behind the screen who helped us to transform an idea into a real application. We would like to express our heart-felt gratitude to our parents without whom we would not have been privileged to achieve and fulfill our dream. We are grateful to our principal, Mr. L.V.N PRASAD who most ably run the institution and has had the major hand in enabling us to do our project. We profoundly thank Dr. K.SRINIVASA REDDY, Head of the Department of Computer Science & Engineering who has been an excellent guide and also a great source of inspiration to our work. We would like to thank our internal guide ASSISSTANT PROFESSOR. Mr. N. Bhaswanth for his technical guidance, constant encouragement and support in carrying out our project at college. The satisfaction and euphoria that accompany the successful completion of the task would be great but incomplete without the mention of the people who made it possible with their constant guidance and encouragement crowns all the efforts with success. In this context, we would like to thank all the other staff members, both teaching and non-teaching, who have extended their timely help and eased our task. VII.REFERENCES 1 Android Developers. (n.d.). Retrieved November 20, 2015, from http://developer.android.com/ 2 Deitel, P. J. (2012). Android for Programmers: an App-driven approach. Upper Saddle River, NJ: Prentice Hall; London: Pearson Education, c2012. 3 Welcome to New Circle. (n.d.). Retrieved November 20, 2015, from https://thenewcircle.com/ 4 Android 6.0 Marshmallow. (n.d.). Retrieved November 20, 2015, from https://developer.android.com 5 Download. (n.d.). Retrieved November 20, 2015, from http://developer.android.com/sdk/index.html 6 X. Chen and A. L. Yuille, “Detecting and reading text in natural scenes,”in Proc. IEEE CVPR, Jun./Jul. 2004, pp. II-366–II-373.7 D. Chen, J.-M. Odobez, and H. Bourlard, “Text detection and recognitionin images and video frames,” Pattern Recognit., vol. 37, no. 3,pp. 595–608, 2004.8 M. R. Lyu, J. Song, and M. Cai, “A comprehensive method for multilingualvideo text detection, localization, and extraction,” IEEE Trans.Circuits Syst. Video Technol., vol. 15, no. 2, pp. 243–255, Feb. 2005.9 T. E. de Campos, B. R. Babu, and M. Varma, “Character recognition in natural images,” in Proc. VISAPP, Feb. 2009, pp. 121–132.10 B. Epshtein, E. Ofek, and Y. Wexler, “Detecting text in natural scenes with stroke width transform,”in Proc. IEEE CVPR, Jun. 2010,pp. 2963–2970