Research on Face Recognition Based on Deep Learning

Haoyu Wang, Lulu Guo

20212021 3rd International Conference on Artificial Intelligence and Advanced Manufacture (AIAM)22 citationsDOI

Abstract

In order to reduce the occurrence of identity theft and promote the fairness of clocking in, face recognition has been attracting increasing attention. In this paper, on the basis of analyzing the advantages and disadvantages of common face recognition methods (facial geometric feature based method, template matching-based method, wavelet feature-based method and PCA-based method), the factors affecting face recognition such as illumination and age are fully considered. By adopting the Convolutional Neural Networks (CNN) model, a face recognition system is designed and implemented. The system test shows that the system can call the camera to recognize human face, and output the name of the recognized person accurately by loading the trained model.

Topics & Concepts

Computer scienceArtificial intelligenceFacial recognition systemConvolutional neural networkFace (sociological concept)Three-dimensional face recognitionPattern recognition (psychology)Feature (linguistics)Feature extractionComputer visionMatching (statistics)WaveletFace hallucinationIdentity (music)Face detectionMathematicsLinguisticsSocial scienceAcousticsStatisticsPhysicsSociologyPhilosophyFace recognition and analysisFace and Expression RecognitionBiometric Identification and Security