A character image enhancement method from characters with various background images
H. Ozawa, Toshiaki Nakagawa · 2002
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.>