An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping Export

@article{citeulike:5378510, abstract = {Abstract\ \ A CAPTCHA is a test designed to distinguish computer programs from human beings, in order to prevent the abuse of networked resources. Academic research into CAPTCHAs includes designing friendly and secure CAPTCHA systems and defeating existing CAPTCHA systems. Traditionally, defeating a CAPTCHA test requires two procedures: segmentation and recognition. Recent research shows that the problem of segmentation is much harder than recognition. In this paper, two new segmentation techniques called projection and middle-axis point separation are proposed for CAPTCHAs with line cluttering and character warping. Experimental results show the proposed techniques can achieve segmentation rates of about 75\%.}, author = {Huang, Shih-Yu and Lee, Yeuan-Kuen and Bell, Graeme and Ou, Zhan-He}, citeulike-article-id = {5378510}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s11042-009-0341-5}, citeulike-linkout-1 = {http://www.springerlink.com/content/8u60303760488000}, doi = {10.1007/s11042-009-0341-5}, journal = {Multimedia Tools and Applications}, keywords = {captcha}, posted-at = {2009-08-26 05:42:13}, priority = {2}, title = {An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping}, url = {http://dx.doi.org/10.1007/s11042-009-0341-5} }

TY - JOUR ID - citeulike:5378510 L3 - citeulike-article-id:5378510 N2 - Abstract  A CAPTCHA is a test designed to distinguish computer programs from human beings, in order to prevent the abuse of networked resources. Academic research into CAPTCHAs includes designing friendly and secure CAPTCHA systems and defeating existing CAPTCHA systems. Traditionally, defeating a CAPTCHA test requires two procedures: segmentation and recognition. Recent research shows that the problem of segmentation is much harder than recognition. In this paper, two new segmentation techniques called projection and middle-axis point separation are proposed for CAPTCHAs with line cluttering and character warping. Experimental results show the proposed techniques can achieve segmentation rates of about 75%. JF - Multimedia Tools and Applications TI - An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping KW - captcha AU - Huang, Shih-Yu AU - Lee, Yeuan-Kuen AU - Bell, Graeme AU - Ou, Zhan-He UR - http://dx.doi.org/10.1007/s11042-009-0341-5 ER -