GAUSSIAN DIFFUSIVE HARTIGAN MULTIDIMENSIONAL DEEP BELIEF DIVERGENCE FEATURE LEARNING USING PARTIAL DIFFERENTIAL EQUATION FOR FACE RECOGNITION
Abstract
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.

Authors
S. Moorthi and S. Karthikeyan
Government Arts College, Salem, India

Keywords
Face Recognition, Feature Learning, Fractional Partial Differential Equation
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
000000110020
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 13 , Issue: 4 , Pages: 3002 - 3012 )
Date of Publication :
May 2023
Page Views :
247
Full Text Views :
9

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.