Face Detecting and Recognizing using 3D local Binary Pattern

Abstract

This study focuses on improving face detection and recognition by using a 3D Local Binary Pattern (3DLBP) approach. While traditional 2D Local Binary Pattern (LBP) methods have been widely used for texture classification, they often fall short when dealing with the complexity of 3D facial textures. To address this limitation, the research applies an enhanced 3DLBP method using the Texan 3D facial recognition dataset. The process involves extracting facial texture features and classifying them through a Support Vector Machine (SVM) to achieve higher accuracy in face recognition. The results reveal that 3DLBP significantly improves recognition performance, especially when distinguishing facial features from different angles and expressions. The findings highlight the potential of this approach for real-world applications such as security, biometric identification, and crime prevention. The paper emphasizes the importance of incorporating more diverse facial data to further refine and optimize the accuracy of live recognition systems