ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

MAPS: midline analysis and propagation of segmentation

Kumar, Deepak and Prasad, Anil MN and Ramakrishnan, AG (2012) MAPS: midline analysis and propagation of segmentation. In: Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, Dec. 17-19, 2012, New York, NY, USA.

[img] PDF
Com_Visi_Gra_Ima_Pro_1_2012.pdf - Published Version
Restricted to Registered users only

Download (232kB) | Request a copy
Official URL: http://dx.doi.org/10.1145/2425333.2425348

Abstract

Scenic word images undergo degradations due to motion blur, uneven illumination, shadows and defocussing, which lead to difficulty in segmentation. As a result, the recognition results reported on the scenic word image datasets of ICDAR have been low. We introduce a novel technique, where we choose the middle row of the image as a sub-image and segment it first. Then, the labels from this segmented sub-image are used to propagate labels to other pixels in the image. This approach, which is unique and distinct from the existing methods, results in improved segmentation. Bayesian classification and Max-flow methods have been independently used for label propagation. This midline based approach limits the impact of degradations that happens to the image. The segmented text image is recognized using the trial version of Omnipage OCR. We have tested our method on ICDAR 2003 and ICDAR 2011 datasets. Our word recognition results of 64.5% and 71.6% are better than those of methods in the literature and also methods that competed in the Robust reading competition. Our method makes an implicit assumption that degradation is not present in the middle row.

Item Type: Conference Paper
Publisher: ACM, Inc
Additional Information: Copyright of this article belongs to ACM, Inc.
Keywords: Segmentation; Text Recognition; Bayesian Classification; Max-Flow; Midline; ICDAR 2003 Dataset; ICDAR 2011 Dataset; Optical Character Recognition; Min-Max Method; Word Recog- nition; Propagation
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 02 Jul 2013 07:49
Last Modified: 02 Jul 2013 07:49
URI: http://eprints.iisc.ac.in/id/eprint/46545

Actions (login required)

View Item View Item