MF-FaceNet: An Intuitive Age-Invariant Face Recognition through Multi-Feature and Multi-Fusion CNNs

MF-FaceNet: An Intuitive Age-Invariant Face Recognition through Multi-Feature and Multi-Fusion CNNs
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-3
Year of Publication : 2023
Author : M. Rajababu, K. Srinivas, H. Ravisankar
DOI : 10.14445/22315381/IJETT-V71I3P243

How to Cite?

M. Rajababu, K. Srinivas, H. Ravisankar, "MF-FaceNet: An Intuitive Age-Invariant Face Recognition through Multi-Feature and Multi-Fusion CNNs," International Journal of Engineering Trends and Technology, vol. 71, no. 3, pp. 407-422, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I3P243

Abstract
In contrast to general face recognition, Age-Invariant Face Recognition (AIFR) seeks to match faces with a significant age difference. Due to the various shapes and textures of the human body, one of its most important steps is the capacity to recognize the various facial features. Poor recognition performance is the result of all these variances. Previous discriminative techniques have typically focused on dividing facial characteristics into age-related and age-invariant components, which results in the loss of face identification information. In terms of facial recognition, deep learning is thought to be a promising method. Several obstacles still exist, despite the advances made in this area. Deep learning has been seen as a promising technique in terms of face recognition. Unfortunately, despite the advances made in this area, there are still several difficulties. This paper presents a Multi-Feature and Multi-Fusion CNN method for accurate AIFR. This proposed system is named as MF-FaceNet. In this proposed system, features of the face images are extracted from the augmented, grey level and Local Binary Pattern (LBP)image datasets. Experiments are conducted for each extracted feature with three individual CNN models such as VGG-16, DenseNet-201 and ResNet-50. In the next phase of experimental investigation, extracted features are fused, and the investigation is carried out with the fusion CNN models like VDe-23, VRe-23, DeRe-23 and VDeRe-23.For this experimentation with individual and Fusion CNN models, extensive results are obtained with the aid of input standard face datasets such as FGNET, CACD and a Live dataset AS-23. Among all three datasets, the best-performed dataset is the AS-23 live dataset, and compared with the three CNN models, the highest testing accuracy of face recognition is obtained from DenseNet-201(94.27%,93.97%,90.07%). In the AS-23 live dataset, in comparison with three fusion models, the VDeRe-23 CNN feature fusion model achieved the best face recognition testing accuracies, such as 94.02%, 91.27% and 90.7%, respectively. Among all the comparisons on three datasets, the DenseNet-201 achieved the best face recognition accuracy, and for the fusion model, VDeRe-23 gave the best recognition accuracy. Our method enhances the AIFR performance on the College dataset (AS-23) when compared to other well-known datasets. Our approach performs better than the current approaches and offers a high level of recognition accuracy.

Keywords
Age-invariant Face Recognition, Convolutional Neural Network Feature Extraction, Feature Fusion, Local Binary Pattern.

References
[1] Shui-Guang Tong, Yuan-Yuan Huang, and Zhe-Ming Tong, "A Robust Face Recognition Method Combining LBP with Multi-Mirror Symmetry for Images with Various Face Interferences," International Journal of Automation and Computing, vol. 16, pp. 671-682, 2019.
Google Scholar | CrossRef | Publisher Link
[2] P.Bala Saiteja et al., "Enhanced Security for ATM Transactions using Facial Verification," SSRG International Journal of Electronics and Communication Engineering, vol. 3, no. 3, pp. 5-7, 2016.
CrossRef | Publisher Link
[3] Yi Sun et al., “Deep Learning Face Representation by Joint Identification-Verification,” Advances in Neural Information Processing Systems, vol. 27, 2014.
Google Scholar | Publisher Link
[4] Anil K. Jain, Karthik Nandakumar, and Arun Ross, “50 Years of Biometric Research: Accomplishments, Challenges, and Opportunities,” Pattern Recognition Letters, vol. 79, pp. 80-105, 2016.
Google Scholar | CrossRef | Publisher Link
[5] Yi Sun et al., “Deepid3: Face Recognition with Very Deep Neural Networks,” arXiv:1502.00873, 2015.
Google Scholar | CrossRef | Publisher Link
[6] Omkar M. Parkhi, Andrea Vedaldi, and Andrew Zisserman, “Deep Face Recognition,” Proceedings of the British Machine Vision Conference (BMVC), Swansea, pp. 41.1–41.12, 2015.
Google Scholar | CrossRef | Publisher Link
[7] Florian Schroff, Dmitry Kalenichenko, and James Philbin “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 815–823, 2015.
Google Scholar | CrossRef | Publisher Link
[8] Qiong Cao et al., "VGGFace2: A Dataset for Recognising Faces Across Pose and Age," 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition, IEEE, pp. 67-74, 2018.
Google Scholar | CrossRef | Publisher Link
[9] Xiang Wu et al., “A Light CNN for Deep Face Representation Noisy Labels,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 11, pp. 2884–2896, 2018.
Google Scholar | CrossRef | Publisher Link
[10] Chandan A D et al., "Survey Paper on Vehicle Security using Facial Recognition & Password," SSRG International Journal of Electronics and Communication Engineering, vol. 9, no. 6, pp. 5-9, 2022.
CrossRef | Publisher Link
[11] Unsang Park, Yiying Tong, and Anil K. Jain, “Age-Invariant Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 5, pp. 947–954, 2010.
Google Scholar | CrossRef | Publisher Link
[12] Haibin Ling et al., “Face Verification Across Age Progression Using Discriminative Methods,” IEEE Transactions on Information Forensics and Security, vol. 5, no. 1, pp. 82–91, 2010.
Google Scholar | CrossRef | Publisher Link
[13] Joyassree Sen et al., "Face Recognition Using Deep Convolutional Network and One-shot Learning," SSRG International Journal of Computer Science and Engineering, vol. 7, no. 4, pp. 23-29, 2020.
Google Scholar | CrossRef | Publisher Link
[14] Bor-Chun Chen, Chu-Song Chen, and Winston H. Hsu, “Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval,” Lecture Notes in Computer Science, vol. 8694, pp. 768–783, 2014.
Google Scholar | CrossRef | Publisher Link
[15] Garima Verma et al., “A Technique for Face Verification Across Age Progression with Large Age Gap,” 4th International Conference on Signal Processing, Computing and Control (ISPCC), vol. 2017, pp. 603–607, 2017.
Google Scholar | CrossRef | Publisher Link
[16] Ya Li et al., “A Deep Joint Learning Approach for Age Invariant Face Verification,” CCF Chinese Conference on Computer Vision, Springer, Berlin, Heidelberg, pp. 296-305, 2015.
Google Scholar | CrossRef | Publisher Link
[17] Yandong Wen, Zhifeng Li, and Yu Qiao, “Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 4893–4901, 2016.
Google Scholar | CrossRef | Publisher Link
[18] Nazia Begum, and Syed Noorullah, “Biometric Uncorrelated Face Recognition Using Unsupervised Learning,” International Journal of Computer Engineering in Research Trends, vol. 7, no. 3, pp. 13–18, 2020.
CrossRef | Publisher Link
[19] Simone Bianco, “Large Age-Gap Face Verification by Feature Injection in Deep Networks,” Pattern Recognition Letters, vol. 90, pp. 36–42, 2017.
Google Scholar | CrossRef | Publisher Link
[20] Ya Li et al., “Distance Metric Optimization Driven Convolutional Neural Network for Age Invariant Face Recognition,” Pattern Recognition, vol. 75, pp. 51–62, 2018.
Google Scholar | CrossRef | Publisher Link
[21] Chenfei Xu, Qihe Liu, and Mao Ye, “Age Invariant Face Recognition and Retrieval by Coupled Auto-Encoder Networks,” Neurocomputing, vol. 222, pp. 62–71, 2017.
Google Scholar | CrossRef | Publisher Link
[22] Opeyemi Oyelesi, and Akingbade Kayode Francis, "Face Recognition for Access Control using PCA Algorithm," SSRG International Journal of VLSI & Signal Processing, vol. 4, no. 2, pp. 22-27, 2017.
CrossRef | Publisher Link
[23] Sai Vamshi Challamalla et al., “Online Attendance Management System Using Face Recognition Techniques,” International Journal of Computer Engineering in Research Trends, vol. 9, no. 8, pp. 158–169, 2022.
CrossRef | Publisher Link
[24] Sabah Afroze et al., “Age Invariant Face Recognition using Frangi2D Binary Pattern,” ACM International Conference Proceeding Series, pp. 8–13, 2019.
Google Scholar | CrossRef | Publisher Link
[25] Amal A. Moustafa, Ahmed Elnakib, and Nihal F. F. Areed, “Optimization of Deep Learning Features for Age-Invariant Face Recognition,” International Journal of Electrical and Computer Engineering, vol. 10, no. 2, pp. 1833–1841, 2020.
Google Scholar | CrossRef | Publisher Link
[26] Ankit Jain, Kirti Bhatia, Rohini Sharma, and Shalini Bhadola, "An Overview on Facial Expression Perception Mechanisms," SSRG International Journal of Computer Science and Engineering, vol. 6, no. 4, pp. 19-24, 2019.
CrossRef | Publisher Link
[27] Hao Wang et al., “Decorrelated Adversarial Learning for Age-Invariant Face Recognition,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, vol. 2019, pp. 3522–3531, 2019.
Google Scholar | CrossRef | Publisher Link
[28] Amal A. Moustafa, Ahmed Elnakib, and Nihal F. F. Areed, “Age-Invariant Face Recognition Based on Deep Features Analysis,” Signal, Image Video Processing, vol. 14, no. 5, pp. 1027–1034, 2020.
Google Scholar | CrossRef | Publisher Link
[29] Bhumika Pathya, and Sumita Nainan, "Performance Evaluation of Face Recognition using LBP, PCA and SVM," SSRG International Journal of Computer Science and Engineering, vol. 3, no. 4, pp. 58-61, 2016.
Google Scholar | CrossRef | Publisher Link
[30] Yangjian Huang, and Haifeng Hu, “A Parallel Architecture of Age Adversarial Convolutional Neural Network for Cross-Age Face Recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 1, pp. 148-159, 2021.
Google Scholar | CrossRef | Publisher Link
[31] Chenggang Yan et al., "Age-Invariant Face Recognition by Multi-Feature Fusionand Decomposition with Self-Attention," ACM Transactions on Multimedia Computing, Communications, and Applications, pp. 1-18, 2022.
Google Scholar | CrossRef | Publisher Link
[32] D. J. Samatha Naidu, and R. Lokesh, "Missing Child Identification System using Deep Learning with VGG-FACE Recognition Technique," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 9, pp. 1-11, 2022.
CrossRef | Publisher Link
[33] Mubarak Albarka Umar et al., “Fighting Crime and Insecurity in Nigeria: An Intelligent Approach,” International Journal of Computer Engineering in Research Trends, vol. 8, no. 1, pp. 6–14, 2021.
Google Scholar | CrossRef | Publisher Link
[34] Caifeng Shan, Shaogang Gong, and Peter W. McOwan, “Facial Expression Recognition Based on Local Binary Patterns: A Comprehensive Study,” Image and Vision Computing, vol. 27, no. 6, pp. 803–816, 2009.
Google Scholar | CrossRef | Publisher Link
[35] R Sindhoori, "Digital image processing. Multi feature face recognition in PSO -SVM," SSRG International Journal of Electrical and Electronics Engineering, vol. 1, no. 3, pp. 1-6, 2014.
CrossRef | Publisher Link
[36] Prasanna Rajendra, Niket Worlikar, Yash Mahajan, Siddhesh Swami, "Smart Surveillance Using OpenCV, Motion Analysis And Facial Landmark," SSRG International Journal of VLSI & Signal Processing, vol. 7, no. 1, pp. 11-14, 2020.
CrossRef | Publisher Link
[37] Gao Huang et al., “Densely Connected Convolutional Networks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 2261-2269, 2017.
Google Scholar | CrossRef | Publisher Link
[38] Noha Ghatwary, Xujiong Ye, and Massoud Zolgharni, “Esophageal Abnormality Detection Using Densenet Based Faster R-CNN with Gabor Features,” IEEE Access, vol. 7, pp. 84374–84385, 2019.
Google Scholar | CrossRef | Publisher Link
[39] D. Betteena Sheryl Fernando et al., "Face Recognition For Home Security," SSRG International Journal of Computer Science and Engineering, vol. 6, no. 10, pp. 7-12, 2019.
CrossRef | Publisher Link
[40] A. Lanitis, C.J. Taylor, and T.F. Cootes, “Toward Automatic Simulation of Aging Effects on Face Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 442–455, 2002.
Google Scholar | CrossRef | Publisher Link
[41] Dihong Gong et al., “Hidden Factor Analysis for Age Invariant Face Recognition,” IEEE International Conference on Computer Vision, pp. 2872–2879, 2013.
Google Scholar | CrossRef | Publisher Link
[42] Yitong Wang et al., “Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition,” European Conference on Computer Vision, vol. 11219, pp. 764–779, 2018.
Google Scholar | CrossRef | Publisher Link
[43] M. Saad Shakeel, and Kin-Man Lam, “Deep-Feature Encoding-Based Discriminative Model for Age-Invariant Face Recognition,” Pattern Recognition, vol. 93, pp. 442–457, 2019.
Google Scholar | CrossRef | Publisher Link
[44] Lingshuang Du, Haifeng Hu, and Yongbo Wu, “Age Factor Removal Network Based on Transfer Learning and Adversarial Learning for Cross-Age Face Recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 9, pp. 2830-2842, 2020.
Google Scholar | CrossRef | Publisher Link
[45] Shiji S K, and Dr. S.H Krishnaveni, "An Analytical Approach for Reconstruction of Cosmetic Surgery Images using EUCLBP and SIFT," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 8, pp. 60-71, 2022.
CrossRef | Publisher Link
[46] Krishna Dharavath, Amarnath Gaini, and Viod Adla, "A Parallel Deep Learning Approach for Age Invariant Face Recognition system," 2022 International Conference on Computer Communication and Informatics, IEEE, pp. 1-6, 2022.
Google Scholar | CrossRef | Publisher Link
[47] Karen Simonyan, and Andrew Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv:1409.1556, 2015.
Google Scholar | CrossRef | Publisher Link
[48] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770–778, 2015.
Google Scholar | CrossRef | Publisher Link
[49] Hae-Min Moon, Chang Ho Seo, and Sung Bum Pan, “A Face Recognition System based on Convolution Neural Network Using Multiple Distance Face,” Soft Computing, vol. 21, no. 17, pp. 4995-5002, 2017.
Google Scholar | CrossRef | Publisher Link