Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Gaussian Diffusive Hartigan Multidimensional Deep Belief Divergence Feature Learning Using Partial Differential Equation for Face Recognition


Affiliations
1 Department of Mathematics, Government Arts College, Salem, India
     

   Subscribe/Renew Journal


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.

Keywords

Face Recognition, Feature Learning, Fractional Partial Differential Equation.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Iman S. Badr, Ahmed G. Radwan, El-Sayed M. EL-Rabaie, Lobna A. Said, Ghada M. El Banby, Walid El-Shafai and Fathi E. Abd El-Samie, “Cancellable Face Recognition based on Fractional-Order Lorenz Chaotic System and HAAR Wavelet Fusion”, Digital Signal Processing, Vol. 116, pp. 1-17, 2021.
  • Rachid Benouinia, Imad Batiouaa, Khalid Zenkouara,, Azeddine Zahia, Said Najaha and Hassan Qjidaa, “Fractional-Order Orthogonal Chebyshev Moments and Moment Invariants for Image Representation and Pattern Recognition”, Pattern Recognition, pp. 1-38, 2018.
  • Sushil Kumar Paul, Saida Bouakaz, Chowdhury Mofizur Rahman and Mohammad Shorif Uddin, “Component-based Face Recognition using Statistical Pattern Matching Analysis”, Pattern Analysis and Applications, Vol. 89, pp. 1-21, 2020.
  • Yun Tao Jia, Min Qiang Xu and Ying Zhen Lin, “A Numerical Solution for Variable Order Fractional Functional Differential Equation”, Applied Mathematics Letters, Vol. 64, pp. 125-130, 2017.
  • Changpin Li and Fanhai Zeng, “Finite Difference Methods for Fractional Differential Equations”, International Journal of Bifurcation and Chaos, Vol. 22, No. 4, pp. 1-28, 2012.
  • N.H. Sweilam, M.M. Khader and H.M. Almarwm, “Numerical Studies for the Variable-Order Nonlinear Fractional Wave Equation”, Fractional Calculus and Applied Analysis, Vol. 15, pp. 669-683, 2012.
  • S. Moorthi and S. Karthikeyan, “Deep Gaussian Multivariate Hosmer-Lemeshow Feature Learning via Partial Differential Equation to Face Recognition”, International Journal of Innovative Computing, Information and Control, Vol. 19, No. 1, pp. 1-17, 2023.
  • Anubha Bhaik, “Detection of Improperly Worn Face Masks using Deep Learning - A Preventive Measure Against the Spread of COVID-19”, International Journal of Interactive Multimedia and Artificial Intelligence, Vol. 7, No 7, pp. 1-13, 2021.
  • H. Yi, “Efficient Architecture for Improving Differential Equations based on Normal Equation Method in Deep Learning”, Alexandria Engineering Journal, Vol.59, No. 4, pp. 2491-2502, 2020.
  • U.A. Usmani, J. Watada, J. Jaafar, I.A. Aziz and A. Roy, “Particle Swarm Optimization with Deep Learning for Human Action Recognition”, International Journal of Innovative Computing, Information and Control, Vol.17, No. 6, pp. 1843-1870, 2021.
  • F.M. Andiani and B. Soewito, “Face Recognition for Work Attendance using Multitask Convolutional Neural Network (MTCNN) and Pre-Trained FaceNet”, ICIC Express Letters, Vol.15, No.1, pp. 57-65, 2021.
  • S. Moorthi and S. Karthikeyan, “Deep Gaussian Multivariate Hosmer-Lemeshow Feature Learning via Partial Differential Equation to Face Recognition”, International Journal of Innovative Computing, Information and Control, Vol.19, No.1, pp. 15-32, 2023.
  • Soumia Djaghbellou, Zahid Akhtar, Abderraouf Bouziane and Abdeoluahab Attia, “Arabic Handwritten Characters Recognition via Multi-Scale Hog Features and Multi-Layer Deep Rule-Based Classification”, ICTACT Journal on Image and Video Processing, Vol. 10, No. 4, pp. 2195-2200, 2020.
  • N.R. Pradeep and J. Ravi, “Machine Learning based Artificial Neural Networks for Fingerprint Recognition”, ICTACT Journal on Image and Video Processing, Vol. 13, No. 2, pp. 2874-2882, 2022.

Abstract Views: 186

PDF Views: 0




  • Gaussian Diffusive Hartigan Multidimensional Deep Belief Divergence Feature Learning Using Partial Differential Equation for Face Recognition

Abstract Views: 186  |  PDF Views: 0

Authors

S. Moorthi
Department of Mathematics, Government Arts College, Salem, India
S. Karthikeyan
Department of Mathematics, Government Arts College, Salem, India

Abstract


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.

Keywords


Face Recognition, Feature Learning, Fractional Partial Differential Equation.

References