Dense hand-CNN: A novel CNN architecture based on later fusion of neural and wavelet features for identity recognition

Abstract

Biometric recognition or biometrics has emerged as the best solution for criminal identification and access control applications where resources or information need to be protected from unauthorized access. Biometric traits such as fingerprint, face, palmprint, iris, and hand-geometry have been well explored; and matured approaches are available in order to perform personal identification. The work emphasizes the opportunities for obtaining texture information from a palmprint on the basis of such descriptors as Curvelet, Wavelet, Wave Atom, SIFT, Gabor, LBP, and AlexNet. The key contribution is the application of mode voting method for accurate identification of a person at the fusion decision level. The proposed approach was tested in a number of experiments at the CASIA and IITD palmprint databases. The testing yielded positive results supporting the utilization of the described voting technique for human recognition purposes.