Title :
A geometric approach to machine-printed character recognition
Author :
Wang, Li ; Pavlidis, Theo
Author_Institution :
Dept. of Comput. Sci., State Univ. of New York, Stony Brook, NY, USA
Abstract :
An approach to feature extraction that eliminates binarization by extracting features directly from gray scale images is presented. It not only allows the processing of poor quality input (e.g., low contrast, dirty images), but also offers the possibility of significantly lower resolution for digitization
Keywords :
character recognition; feature extraction; geometry; image recognition; digitization; dirty images; feature extraction; geometry; gray scale images; image resolution; low contrast; machine-printed character recognition; poor quality input processing; Character recognition; Computer science; Feature extraction; Graphics; Image resolution; Image sensors; Optical character recognition software; Printers; Shape; Surface topography;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223206
