A new algorithm for text segmentation based on stroke filter英文电子资料.pdfVIP

A new algorithm for text segmentation based on stroke filter ZHANG Xiu-li , SHI Zhen-gang College of Information Science and Engineering ,Shenyang Ligong University, Shenyang, 110168,China E-mail: syluzx@ Abstract: In order to solve segment text accurately and robustly from a complex background. This paper propose a new algorithm for text segmentation in images by using a stroke filter. In this paper, we design a new algorithm for text segmentation by using the stroke filter. First, we describe the stroke filter briefly based on local region analysis. Second, the determination of text color polarity and local region growing procedures are performed based on the response of the stroke filter. Finally, the feedback procedure by the recognition score from an optical character recognition (OCR) module is used to improve the performance of text segmentation. The proposed algorithm is compared with other algorithms. The experimental results demonstrate that the proposed algorithm obtained satisfactory results. Key Words: Text segmentation, Complex background, Optical character recognition(OCR), Stroke filter Design of stroke filter INTRODUCTION A stroke is defined as a straight line or arc used as a The extraction of text information is very important segment of text, and the texts in images comprise one or because texts in images and videos contain important and