Character segmentation and recognition algorithm of text region in steel images
Keunhwi Koo, Jong Pil Yun, SungHoo Choi, Jonghyun Choi, Doo-chul Choi, Sang Woo Kim · International Conference on Signal Processing · 2009
There are many algorithms for character segmentation [1]. Many people have been making researches in segmentation of touching or overlapping character up to now, but most of algorithms cannot apply to the text region of slab management numbers marked on the slab in the steel image. Because the text regions are irregular such as touching character by strong illumination and by trouble of nozzle in marking machine, and loss of character. It is difficult to gain high success rate in all cases This paper proposes a new algorithm for character segmentation using combined profile analysis and recognition based method. Besides the proposed algorithm converts gray image to binary image using method of adjusting brightness and contrast in pre-processing step. The experimental results show high recognition rates of slab management numbers marked on the slab about various text region images.