Abstract In this paper, a text extraction method for the complex color image with image enhancement by Symmetric Neighborhood Filters(SNF) is proposed. Firstly, the original image is enhanced by SNF and the generate edge feature map on the enhanced image is obtained. The candidate text regions are then generated by merging the bounding blocks which are extracted by utilizing the edgebased connectedcomponent searching method and taking the edgedivided color information into consideration. Finally, the texture and stroke feature of the text are used to eliminate the false candidates. Experimental results show this method can extract the text including Chinese and English characters accurately. It is the key point to ensure the success of extraction method that the original image is enhanced by SNF because SNF not only smoothes the interior of the image but keeps the true edges of the image.
[1] Fletcher L A, Kasturi R. A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images. IEEE Trans on Pattern Analysis and Machine Intelligence, 1988, 10(6): 910-918 [2] Jung K, Kim K I, Han J H. Text Extraction in Real Scene Images on Planar Planes // Proc of the 16th International Conference on Pattern Recognition. Washington, USA: IEEE Computer Society, 2002, Ⅲ: 469 -472 [3] Gao J, Yang J. An Adaptive Algorithm for Text Detection from Natural Scenes // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA, 2001, Ⅱ: 84-89 [4] Quan Wei, Zheng Nanning, Jia Xinchun. Research on Vehicle License Plate Character Extraction from Complex Background. Information and Control, 2002, 31(1): 25-29 (in Chinese) (权 炜,郑南宁,贾新春.复杂背景下的车辆牌照字符提取方法研究. 信息与控制,2002, 31(1): 25-29) [5] Westman T, Harwood D, Laitinen T, et al. Color Segmentation by Hierarchical Connected Components Analysis with Image Enhancement by Symmetric Neighborhood Filters // Proc of the 10th International Conference on Pattern Recognition. Atlantic City, USA, 1990: 796-802 [6] Li Zaiming, et al. The Technology of Digital Image Processing ard Compressing. Chengdu, China: University of Electronic Science and Technology of China Press, 2000 (in Chinese) (李在铭,等.数字图像处理压缩与识别技术.成都:电子科技大学出版社,2000) [7] Zhu S C, Yullie A L. FORMS: A Flexible Object Recognition and Modeling System. International Journal of Computer Vision, 1996, 20(3): 187-212
2006, Vol. 19 
