Title :
A character image enhancement method from characters with various background images
Author :
Ozawa, Hideaki ; Nakagawa, Toru
Author_Institution :
NTT Human Interface Lab., Kanagawa, Japan
Abstract :
A method which converts characters with complex backgrounds into black characters with plain white backgrounds is proposed. The method first transforms the spatial gray-level images that represent the geometric patterns into real gray-level images. The method then distinguishes the gray level of the characters from the gray level of the background images. The proposed algorithm is applied to many headlines published in Japanese newspapers, and its performance for enhancing character extraction is confirmed
Keywords :
document image processing; image enhancement; optical character recognition; Japanese newspapers; background images; black characters; character extraction; character image enhancement method; geometric patterns; headlines; performance; plain white backgrounds; spatial gray-level images; Books; Character recognition; Humans; Image converters; Image enhancement; Laboratories; Licenses; Optical character recognition software; Pixel; Vehicles;
Conference_Titel :
Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
Conference_Location :
Tsukuba Science City
Print_ISBN :
0-8186-4960-7
DOI :
10.1109/ICDAR.1993.395782
