Segmentation and extraction of text from curved text lines using image processing approach

摘要

The camera captured images containing text are having curved text lines because of distortions by page curl and the view angle of camera. So it is necessary while scanning the document, the text should be straight and words are inline properly. But text lines segmentation of curled text is a difficult method for dewraping techniques. This paper presents the method based on image processing algorithms for segmentation and extraction of characters from curled text lines from document images. The algorithm performs the curved text segmentation using x-line and base line. The words in the document image are identified and bounding boxes are plotted around the words. The properties of connected components are used for segmentation of words. This algorithm achieved good accuracy for extraction of characters from curved text lines.