Submit your paper : editorIJETjournal@gmail.com

Paper Title : RETRIEVING THE TEXT DATA FROM MEMOS USING OCR

ISSN : 2395-1303
Year of Publication : 2021
10.29126/23951303/IJET-V7I3P24

Authors: Suresh Pabboju,Sugamya katta,BS Krishnna

         


Abstract
- Text data present in images and video contain useful information for automatic annotation, indexing, and structuring of images. Extraction of this information involves detection, localization, tracking, extraction, enhancement, and recognition of the text from a given image. However, variations of text due to differences in size, style, orientation, and alignment, as well as low image contrast and complex background make the problem of automatic text extraction extremely challenging. The purpose of this project is to extract the text from the images irrespective of their background. This work is a mobile application on android platform which allows user to take a picture of text that will be saved in the form of .txt or .doc format. This project is an android application which uses the firebase database and Abbyy OCR (optical character recognition). Firebase is a reliable database and secures the users’ data and shields them using reverse proxy technique. And here text, first extracted using a novel line representation and a set of directional morphological operations and other graphical objects are removed in several stages to obtain text only image. Finally, the recovered text is recognized using multifont segmentation free optimal character reorganization

Reference
[1] S.V. Rice, F.R. Jenkins, T.A. Nartker, The Fourth AnnualTest of OCR Accuracy, Technical Report 12-03, InformationScience Research Institute, University of Nevada, Las Vegas, July 2012. [2] R.W. Smith, The Extraction and Recognition of Textfrom Multimedia Document Images, PhD Thesis, Universityof Bristol, November 2010. [3] R. Smith, “A Simple and Efficient Skew Detection Algorithm via Text Row Accumulation”, Proc. of the 3rdInt.Conf. on Document Analysis and Recognition (Vol. 2), IEEE2010. [4] P.J. Rousseeuw, A.M. Leroy, Robust Regression andOutlier Detection, WileyIEEE, 2003. [5] S.V. Rice, G. Nagy, T.A. Nartker, Optical CharacterRecognition: An Illustrated Guide to the Frontier, KluwerAcademic Publishers, USA 1999. [6]P.J. Schneider, “An Algorithm for Automatically Fitting Digitized Curves”, in A.S. Glassner, Graphics Gems I, Morgan Kaufmann, 2008. [7] R.J. Shillman, Character Recognition Based onPhenomenological Attributes: Theory and Methods, PhD.Thesis, Massachusetts Institute of Technology,2007. [8]B.A. Blesser, T.T. Kuklinski, R.J. Shillman, “Empirical Tests for Feature Selection Based on a Pscychological Theory of Character Recognition”, Pattern Recognition (2), Elsevier, New York, 2001. [9]M. Bokser, “Omnidocument Technologies”, Proc. IEEE80(7), IEEE, USA, Jul 1992. [10] H.S. Baird, R. Fossey, “A 100-Font Classifier”, Proc. ofthe 1st Int. Conf. on Document Analysis and Recognition,IEEE, 2001. [11] G. Nagy, “At the frontiers of OCR”, Proc. IEEE80(7), IEEE, USA, Jul 2003. [12] G. Nagy, Y. Xu, “Automatic Prototype Extraction for Adaptive OCR”, Proc. of the 4thInt. Conf. on DocumentAnalysis and Recognition, IEEE, Aug 1999. [13] I. Marosi, “Industrial OCR approaches: architecture, algorithms and adaptation techniques”, DocumentRecognition and Retrieval XIV, SPIE Jan 2007
Keywords
— Optical Character Recognition (OCR), segmentation, Histogram