Skip navigation
Please use this identifier to cite or link to this item:
Title: Signature segmentation from machine printed documents using contextual information
Authors: Mandal R.
Pratim Roy, Partha
Pal U.
Published in: International Journal of Pattern Recognition and Artificial Intelligence
Abstract: Automatic signature segmentation from a printed document is a challenging task due to the nature of handwriting of the signatory, overlapping/touching of signature strokes with printed text, graphics, noise, etc. In this paper, we propose a two-stage approach for signature segmentation from a document page. In the first stage, a document is segmented into blocks and then blocks are classified into two classes: signature block and printed word block. Gradient-based features are used for block feature extraction and support vector machine classifier is used for block-wise classification. In the second stage, printed characters that may be present in isolated form or overlapped/touched with signature part are removed from signature blocks. From each of the detected signature blocks, the isolated printed characters (if exist) are removed using context information. To detect overlapping/touching printed stroke in a signature block, at first some hypothetical zones are detected where possible overlapping/touching may occur. Bounding box information of neighboring printed word block and local linearity of character strings near the signature blocks are used to detect hypothetical zones. Next, to detect the overlapping/touching printed strokes in hypothetical zones of a signature block, the corner points of contours obtained by Douglas and Peucker polygonal approximation algorithm and skeleton junction points are used. Finally, the touching strokes of signature are separated from text characters using the contour smoothness information near skeleton junction points. The experiment is performed in "Tobacco- 800" dataset [The legacy tobacco document library (ltdl), available at , University of California, San Francisco, 2007.] and the results obtained from the experiment are promising. © World Scientific Publishing Company.
Citation: International Journal of Pattern Recognition and Artificial Intelligence (2012), 26(7): -
Issue Date: 2012
Keywords: handwritten stroke analysis
printed/handwritten text separation
Signature segmentation
ISSN: 2180014
Author Scopus IDs: 54410932900
Author Affiliations: Mandal, R., Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India
Roy, P.P., Laboratoire d'Informatique, Université François Rabelais, Tours, France
Pal, U., Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India
Funding Details: his Ph.D. from the Indian Statistical Institute in 1997 and his Ph.D. work was on the development of Printed Bangla OCR system. He did his post doctoral research on the segmentation of touch- ing English numerals at INRIA (Institut National de Recherche en Informatique et en Auto-matique), France. Since January 1997, he has been a faculty member of the Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata and currently he is a professor. His primary research is digital document processing. He has published 212 research papers in various international journals, conference proceedings and edited volumes. In 1995, he received the student best paper award from the Chennai Chapter of Computer Society of India. He received a merit certi¯cate from the Indian Science Congress Association in 1996. Because of his signi¯cant impact on the document analysis research domain of Indian language, the TC-10 and TC-11 committees of IAPR (International Association for Pattern Recognition) presented the \ICDAR Outstanding Young Researcher Award" to Dr. Pal in 2003. In 2005?2006 Dr. Pal has received JSPS fellowship from the Japanese government. In 2008, 2011 and 2012, Dr. Pal received visiting fellowship from the Spanish, French and Australian governments, respectively. He has collaborated internationally with different countries like Australia, Canada, France, Japan, Norway, Singapore, Spain and Sri Lanka. Also he is co-supervising Ph.D. students at some of the universities of Australia, France, Norway and Spain. Dr. Pal has been serving as a program committee member of many conferences including the International Conference on Document Analysis and Recognition (ICDAR), International Conference on Frontiers of Handwritten Recognition (ICFHR), International Conference on Pattern Recognition (ICPR), Internal Workshop on Document Analysis and Systems (DAS), etc. He is an editorial board member of International Journal of Computer, Mathematical Sciences and Applications; Electronic Letters on Computer Vision and Image Analysis; and ACM Transactions on Asian Language Information Processing. Also he has served as the guest editor of special issues of VIVEK, Electronic Letters on Computer Vision and Image Analysis, and International Journal on Document Analysis and Recognition. He has served as Program-Chair for ICDAR-2009 and DAS-2012 and Organizing Chair for ICFHR-2010. He is a life member of IUPRAI (Indian unit of IAPR) and senior life member of the Computer Society of India.
Corresponding Author: Mandal, R.; Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India; email:
Appears in Collections:Journal Publications [CS]

Files in This Item:
There are no files associated with this item.
Show full item record

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.