Enhancing curvature scale space features for robust shape classification

Kopf, Stephan ; Haenselmann, Thomas ; Effelsberg, Wolfgang

Preview

PDF
Kopf_2005a.pdf - Published
Download (548kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/38960
Additional URL:	http://dx.doi.org/10.1109/ICME.2005.1521464
URN:	urn:nbn:de:bsz:180-madoc-389606
Document Type:	Conference or workshop publication
Year of publication:	2005
Book title:	2005 IEEE International Conference on Multimedia and Expo (ICME) : July 6-8, 2005, Amsterdam, the Netherlands
Volume:	1
Page range:	478-481
Date of the conference:	2005
Place of publication:	Piscataway, NJ
Publishing house:	IEEE Operations Center
ISBN:	0-7803-9331-7
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Praktische Informatik IV (Effelsberg -2017)
Subject:	004 Computer science, internet
Keywords (English):	character recognition , code standards , image classification , image enhancement , image representation , image segmentation , video coding , CSS , MPEG-7 standard ,automatic character recognition,concave-convex segmentation
Abstract:	The curvature scale space (CSS) technique, which is also part of the MPEG-7 standard, is a robust method to describe complex shapes. The central idea is to analyze the curvature of a shape and derive features from inflection points. A major drawback of the CSS method is its poor representation of convex segments: Convex objects cannot be represented at all due to missing inflection points. We have extended the CSS approach to generate feature points for concave and convex segments of a shape. This generic approach is applicable to arbitrary objects. In the experimental results, we evaluate as a comprehensive example the automatic recognition of characters in images and videos.