vioft2nntf2t|tblJournal|Abstract_paper|0xf4ffb2c9320000007aac130001000200
Human face recognition has the most noteworthy role in detecting a person in many real-world scenarios in computer vision like identification, authentication, security, and so on. Face recognition typically acquires the features and compares them to a dataset to discover the best match. The existing methods failed to accurately extract the robust features for face recognition. To solve these issues, Gaussian Diffusive Hartigan Multidimensional Deep Belief Divergence Feature Learning (GDH-MDBDFL) method is proposed based on the Fractional Partial Differential Equation (FPDE) for face recognition. The proposed GDH-MDBDFL method is designed to improve the accuracy of face recognition using FPDE. The proposed GDH-MDBDFL method comprises three different layers such as input, output, and four hidden layers. Both qualitative and quantitative result analysis is presented to verify the effectiveness of the proposed GDH-MDBDFL method. The simulation results, the proposed GDH-MDBDFL method gives the higher recognition accuracy, and precision with lesser recognition time compared to the conventional methods.