Comparative analysis of machine learning algorithms for Lip print based person identification

摘要: Human identification is centered on the theory that every individual unique and has distinct characteristics. Various metrics like Fingerprints, DNA Retina can be used for this purpose. Nonetheless, there still a need reliable alternatives in order to establish identity of an occasions where above techniques are unavailable. Cheiloscopy technique identifying based lip prints. It finds applications medical fields predominantly forensic odontology. The patterns formed human lips it’s shape found individual. Patterns perpetual unless subjected major trauma or alterations. Analogous existing bio metrics, Lip prints serve purpose confirming individual’s identity. main objective work design robust computer-aided system would identify solely lip-prints across diverse datasets. Local Binary extract texture features from segmented upper lower lip. Shape related also extracted as part feature extraction process. Finally, classified using various classifiers Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Ensemble Neural Networks. Performance each classifier analyzed. classification results showed regions satisfactorily person uniquely.