模式识别与人工智能
模式識彆與人工智能
모식식별여인공지능
Moshi Shibie yu Rengong Zhineng
2014年
3期
235-241
,共7页
尹龙%尹东%张荣%王德建
尹龍%尹東%張榮%王德建
윤룡%윤동%장영%왕덕건
验证码识别%扭曲粘连字符%密集尺度不变特征变换( DENSE SIFT)%随机抽样一致性算法( RANSAC)
驗證碼識彆%扭麯粘連字符%密集呎度不變特徵變換( DENSE SIFT)%隨機抽樣一緻性算法( RANSAC)
험증마식별%뉴곡점련자부%밀집척도불변특정변환( DENSE SIFT)%수궤추양일치성산법( RANSAC)
CAPTCHA Recognition%Distorted and Merged Character%Dense Scale Invariant Feature Transform ( DENSE SIFT)%Random Sample Consensus ( RANSAC)
验证码识别研究能及时发现验证码的安全漏洞，使其变得更加安全。扭曲粘连字符验证码能抵抗字符分割，是验证码识别中的难点。针对由扭曲粘连字符构成的验证码，提出一种基于密集尺度不变特征变换( DENSE SIFT)和随机抽样一致性算法( RANSAC)的识别方法。首先通过 DENSE SIFT 特征匹配获得匹配点集，再利用RANSAC算法获取匹配信息，最后采用队列式分析算法得出识别结果。实验表明，该方法对不同难度级别的扭曲粘连验证码均有较好的效果。
驗證碼識彆研究能及時髮現驗證碼的安全漏洞，使其變得更加安全。扭麯粘連字符驗證碼能牴抗字符分割，是驗證碼識彆中的難點。針對由扭麯粘連字符構成的驗證碼，提齣一種基于密集呎度不變特徵變換( DENSE SIFT)和隨機抽樣一緻性算法( RANSAC)的識彆方法。首先通過 DENSE SIFT 特徵匹配穫得匹配點集，再利用RANSAC算法穫取匹配信息，最後採用隊列式分析算法得齣識彆結果。實驗錶明，該方法對不同難度級彆的扭麯粘連驗證碼均有較好的效果。
험증마식별연구능급시발현험증마적안전루동，사기변득경가안전。뉴곡점련자부험증마능저항자부분할，시험증마식별중적난점。침대유뉴곡점련자부구성적험증마，제출일충기우밀집척도불변특정변환( DENSE SIFT)화수궤추양일치성산법( RANSAC)적식별방법。수선통과 DENSE SIFT 특정필배획득필배점집，재이용RANSAC산법획취필배신식，최후채용대렬식분석산법득출식별결과。실험표명，해방법대불동난도급별적뉴곡점련험증마균유교호적효과。
The study of CAPTCHA recognition can discover CAPTCHA security vulnerabilities in time to make it more secure. Distorted and merged CAPTCHA can resist character segmentation, which is the difficult in CAPTCHA recognition. An approach based on DENSE SIFT and RANSAC algorithm is presented for recognition of distorted and merged CAPTCHA. Firstly, matching set is obtained through the matching of DENSE SIFT. Then, matching information is got by using RANSAC algorithm. Finally, recognition results are acquired by means of queue-analysis algorithm. The experimental results show that the proposed method has good performance on CAPTCHAs in different levels of difficulty.
