Multi-oriented Complex Text Recognition using Background and Foreground Information
Speaker: Associate Professor Umapada Pal, Computer Vision and Pattern Recognition Unit, Indian Statistical In
When: 2008-06-13 09:00:00
Venue: 78-420
Host: Professor Brian Lovell
Abstract:In graphical documents (map, engineering drawing), artistic documents etc.
there exist many printed materials where text lines are multi-oriented and
curve in nature. (Some examples of such documents are shown as follows). OCR
of such documents is very difficult with compare to normal text. In this
talk, at first, we propose a novel method to extract individual text lines
from such multi-oriented and curve documents and the method is based on the
foreground and background information of the documents. Here the background
information is taken care of using the concept of water reservoir principle.
Next individual characters will be segmented from the document lines. For
recognition of segmented multi-oriented and multi-sized characters, we will
discuss a scheme where features are invariant to character orientation and
it is based on angular information of the contour pixels of the character.
Finally, we plan to show some demonstrations of the systems developed for
the purpose.
Biography:Umapada Pal received his Ph.D in 1997 from Indian Statistical Institute. His
PhD work was on the development of printed Bangla OCR system. He did his
Post Doctoral research at INRIA, France. From January 1997, he is a Faculty
member of the Computer Vision and Pattern Recognition Unit, Indian
Statistical Institute, Kolkata and his main research area is Document Image
Analysis. He has published 106 research papers in various international
journals, conference proceedings and edited volumes. He received CIMPA
(International Center for Pure and Applied Mathematics) -UNESCO fellowships
for two times. He received a merit certificate from Indian Science Congress
Association in 1996. Because of his significant impact in the Document
Analysis research domain of Indian language, TC-10 and TC-11 committees of
IAPR (International Association for Pattern Recognition) presented 'ICDAR
Outstanding Young Researcher Award' to Dr. Pal in 2003. In 2005-2006 Dr. Pal
has received JSPS fellowship from Japan government. In 2005 he received the
best paper award from the International Conference on Cognition and
Recognition. Dr. Pal has been serving as a program committee member of many
conferences including International Conference on Document Analysis and
Recognition (ICDAR), International Workshop on Document Image Analysis for
Libraries (DIAL), International Workshop on Frontiers of Handwritten
Recognition (IWFHR), Document Analysis Systems (DAS), International
Conference on Pattern recognition (ICPR) etc. Also, he is the Asian PC-Chair
for 10th ICDAR to be held at Barcelona, Spain in 2009. He has served as the
guest editor of special issue of VIVEK journal as well as the journal of
Electronic Letters on Computer Vision and Image Analysis. He is a life
member of IUPRAI (Indian unit of IAPR) and senior life member of Computer
Society of India.
Type: ITEE Seminar
Contact:Professor Brian Lovell, seminar host (lovell@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)