期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2016
卷号：11
期号：11
页码：1
出版社：SERSC
摘要：Fingerprint authentication systemshave been widely deployed in bothcivilian and governmentapplications,however,whether fingerprint authenticationsystemsis securityor not has been an important issue under fraudulent attempts through artificialspoof fingerprints.In this paper,inspired by popularfeature descriptors such as gray level co-occurrence matrix (GLCM)and Gradient (difference matrix (DM)), we propose a novelsoftware-based fingerprint liveness detection algorithmcalled difference co-occurrencematrix(DCM).In doingso, quantization operation is firstly conducted on the images. DMs are constructed by calculatingdifference matrices of horizontal and vertical pixelvalues of images;difference co-occurrence arrays are constructed from thedifference matricesbetween adjacent pixels. To reduce the influence of abnormal pixel values, truncationis used for DMs. Then, we compute four parameters (Angular Second Moment, Entropy, Inverse Differential Moment and Correlation) used as feature vectors of fingerprint images. For the first timein the fingerprint liveness detection, weconstruct eight difference co-occurrence matricesand extract texturefeaturesfrom processed DCMs.Finally,SVMclassifier is used topredictclassificationaccuracy.The experimental results revealthat our proposed method can achieve moreaccurate classificationcomparedwiththe best algorithms of2013Fingerprint Liveness Detection Competition, while being able to recognize spoofed fingerprintswith a better degree of
