Empirical Performance Evaluation Methodology and its Application to Page Segmentation Algorithms

Abstract

Text extraction in an image is a challenging task in the computer vision. Text extraction plays an important role in providing useful and valuable information. Text line segmentation is a major component for document image analysis. Text in documents depend upon various factors such as language, styles, font, sizes, color, background, orientation, fluctuating text lines, crossing or touching text lines. The ascending approach to segmentation of scanned documents in the area of background, text, and photographs is considered. Such classification algorithms can also be used in the printing industry for selective or enhanced scanning and object-oriented rendering. We propose a page-layout-segmentation technique to extract text from scanned documents and also extract each character from the image.

Keywords: character extraction, document image, Image segmentation, page segmentation, X-Y Cut Technique text extraction.