Authors: G. Arunalatha; M. Ezhilarasan
Addresses: Department of Computer Science and Engineering, Pondicherry Engineering College, Puducherry – 605 014, India ' Department of Information Technology, Pondicherry Engineering College, Puducherry – 605 014, India
Abstract: Biometrics refer to automated recognition of individuals based on their biological and behavioral characteristics. Biometric systems are widely used for security. But biometric systems are vulnerable to a certain type of attack. The type 1 attack or direct attack is done at the sensor level using fake input. Spoofing refers to the fraudulent action by an unauthorised person into biometric systems using fake input that reproduces one of the authorised person's biometric inputs. Liveness detection provides an extra level of authentication to biometrics. The fingerprint liveness detection is performed by measuring the following features of the fingerprint. They are Gabor-Shen feature, orientation flow feature, and frequency domain feature. This approach is based on fingerprint image quality. The SVM classifier is used for classification. The ATVS database is used for conducting experiments. This technique is software based as it requires no external hardware. This approach is inexpensive.
Keywords: fingerprint biometrics; liveness detection; fake input; real; spoofing; fingerprints; security; image quality; Gabor-Shen features; orientation flow features; frequency domain; SVM; support vector machines.
International Journal of Internet Protocol Technology, 2016 Vol.9 No.4, pp.196 - 206
Available online: 29 Dec 2016 *Full-text access for editors Access for subscribers Purchase this article Comment on this article