Tesseract Vs Gocr A Comparative Study
Shivani Dhiman1, A .J Singh2
1Ms. Shivani Dhiman, Department of Computer Science, Himachal Pradesh University, Shimla (Himachal Pradesh), India.
2Dr. A.J Singh, Professor, Department of Computer Science, Himachal Pradesh University, Shimla (Himachal Pradesh), India.
Manuscript received on 21 September 2013 | Revised Manuscript received on 28 September 2013 | Manuscript published on 30 September 2013 | PP: 80-83 | Volume-2 Issue-4, September 2013 | Retrieval Number: D0788092413/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Optical Character Recognition (OCR) is a technique used to convert scanned images into machine readable text formats. Different types of Optical Character Recognition (OCR) Tools are used in market from earlier times have their own strengths and weaknesses. They provided different results on the basis of different metrics or parameters. But in this paper we are going to compare two open source tools i.e. Tesseract and GOCR. This paper firstly provides the introduction of open source tools Tesseract and GOCR, architecture of Tesseract and description about their working. In this paper, Tools are compared on the basis of Precision as well as Accuracy by considering different parameters that are Image Type, Resolution, Brightness and Font Type.
Keywords: Optical Character Recognition (OCR), Open Source, Tesseract and GOCR.
Scope of the Article: Study and Experience Reports