Title :
Recognizing Planar Symbols with Severe Perspective Deformation
Author :
Li, Linlin ; Tan, Chew Lim
Author_Institution :
Dept. of Comput. Sci., Nat. Univ. of Singapore, Singapore, Singapore
fDate :
4/1/2010 12:00:00 AM
Abstract :
A common problem encountered in recognizing real-scene symbols is the perspective deformation. In this paper, a recognition method resistant to perspective deformation is proposed, based on Cross-Ratio Spectrum descriptor. This method shows good resistance to severe perspective deformation and good discriminating power to similar symbols.
Keywords :
character recognition; object recognition; cross-ratio spectrum descriptor; perspective deformation; planar symbol recognition; Symbol recognition; perspective deformation.;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2009.196
