TEXT LOCALIZATION USING IMAGE CUES AND TEXT LINE INFORMATION英文电子资料.pdfVIP

Proceedings of 2010 IEEE 17th International Conference on Image Processing September 26-29, 2010, Hong Kong TEXT LOCALIZATION USING IMAGE CUES AND TEXT LINE INFORMATION Toan Nguyen Dinh, Jonghyun Park, Gueesang Lee Department of Electronics and Computer Engineering, Chonnam National University, Korea ABSTRACT Text localization is an important task in text understanding systems. In this paper, an efficient connected component based text localization method is proposed. Two image cues, edge and color, are combined to extract candidate text regions. The non-text regions in these candidate text regions are then removed by the text line information generated from 2D tensor voting. The images in ICDAR 2003 competition dataset are used to evaluate the proposed method. The experimental results show that the proposed method extracts more text regions with a low false positive rate. Index Terms— text localization, image cues, tensor voting, connected component Fig. 1. Proposed method flowchart. 1. INTRODUCTION components are hard to be segmented accurately by using a single image cue such as edge. Text localization is an important part in text image In this paper, a novel CC-based text localization method information extraction systems [1]. Text localization in is proposed. To overcome these problems, we combine both natural scene images is a challenging task due to the edge and color to generate more text regions. Inste