Preprocessing algorithms for Chinese handwriting recognition
Song Gang · Journal of Shandong University · 2007
A series of complete and systematic algorithms on preprocessing of a handwritten image is proposed for free-format handwritten Chinese characters.The connected character removal is carried out by combining statistical characteristic of character width with the Gauss distribution.According to the location of the valley point on projecting images,a threshold value is selected as the best division point resulting in the easy realization of size normalizing and character mosaic and line slope correction.The proposed methods make the whole preprocessing subsystem more stable and perfect,which lays a dependable foundation for subsequent handwriting recognition.