Finger knuckle pattern person identification system based on LDP-NPE and machine learning methods

Biometric-based individual distinguishing proof is a successful strategy for consequently perceiving, with high certainty, an individual's character. The utilization of finger knuckle pictures ID has shown promising outcomes and produced ton interest in biometrics. By seeing that the surface example delivered by twisting profoundly particular, this paper we present new biometric validation framework utilizing finger-knuckle-print (FKP) imaging. In paper, another methodology view neighborhood examples proposed. Local derivative pattern (LDP) histogram investigated FKP description. Then based on preserving embedding (NPE) used dimension reduction to feature vector. extraction method computed evaluated identification task. machine learning methods (multiclass support vector (MSVM), random forest (RF), k-nearest neighbor (KNN)) are proposed classification. system tested PolyU database. empirical results proved model best RF. Moreover, our LDP-NPE been show remarkable efficiency comparison previous work. Experimentally, better accuracy as reflected 99.65%.