Title :
Robust character recognition in FA
Author :
Daito, A. ; Ito, Kei ; Kawagoe, Takazumi ; Murosaki, T. ; Shiose, M.
Author_Institution :
Machinery & Tools Dept., DENSO Corp., Chita, Japan
Abstract :
In FA, the character with a crack or dirt cannot be recognized by pattern matching. Then, we have studied a robust character recognition with template matching and SVM (Support Vector Machine). After classifying some similar characters by template matching, one character is determined by SVM (Support Vector Machine) that is a set of related supervised learning methods. As a result, we achieved the detection margin and adjustment Time shortening.
Keywords :
image classification; image matching; learning (artificial intelligence); optical character recognition; support vector machines; FA; SVM; adjustment time shortening; character classification; crack; detection margin; dirt; image processing; robust character recognition; supervised learning methods; support vector machine; template matching; Cavity resonators; Character recognition; Data mining; Education; Feature extraction; Pattern matching; Support vector machines; Image Processing; SVM; Template matching; character recognition;
Conference_Titel :
SICE Annual Conference (SICE), 2012 Proceedings of
Conference_Location :
Akita
Print_ISBN :
978-1-4673-2259-1
