A Method for Character String Extraction from Binary Images Using Hough Transform

摘要: This paper describes a method for extracting character strings which have various directions and sizes. In this method, we regard string as line segment width is equal to the size, extract (character string) using robust detection Hough Transform. The voting scheme of transform improved from black pixel-base segmentbase, contributes improvement accuracy reduction processing time. order estimate performance our it was applied 15 free formed images (512 x 512 pixels) involving about 60 strings. As result, almost were correctly extracted.