Mayas Publications logo
Buy Books Buy journals

Journal Issues

Back To Archive
Face Biometric Prediction and cyber-attacks experienced Using Deep Learning Model
K. Manikandan
Pages: 1-6 | First Published: 05 Mar 2022
Full text | Abstract | Purchase | References | Request permissions

Abstract
Identify the Face biometric prediction by using digital image processing techniques as well as deep learning model. So we introduce image processing and deep learning technique to determine face at initial stage. Initially, the source images are collected from by using the U-Net based technique. And also extract the features from input image. Finally, classify the images as diseases affected or healthy as classify by using Deep Convolution Generative Adversarial Network (DCGAN). In this proposed model, experimentation is conducted using the python OpenCV model, and the performance is evaluated using different performance measures, which is designated in the result section. During the feature extraction process, the threshold values are also dynamically modified. The CNN's advantage is clear because of the uncertainty caused by noise. In the proposed method, 97.94 percent of the data was correctly classified.
Keywords— Adversarial Network , U-Net based technique

Reference 
1. Hernandez-Ortega J, Fierrez J, Morales A, Galbally J. Introduction to face presentation attack detection. InHandbook of Biometric Anti-Spoofing 2019 (pp. 187-206). Springer, Cham.
2. Daniel N, Anitha A. Texture and quality analysis for face spoofing detection. Computers & Electrical Engineering. 2021 Sep 1;94:107293.
3. Rabie A, Handmann U. Multi-modal biometrics for real-life person-specific emotional human-robot-interaction. In2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014) 2014 Dec 5 (pp. 344-349). IEEE.
4. Kavitha P, Vijaya K. Optimal feature-level fusion and layered k-support vector machine for spoofing face detection. Multimedia Tools and Applications. 2018 Oct;77(20):26509-43.
5. Leitch R. Creatively researching children’s narratives through images and drawings. InDoing visual research with children and young people 2009 May 7 (pp. 59-80). Routledge.
6. Komulainen J, Hadid A, Pietikäinen M. Context based face anti-spoofing. In2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS) 2013 Sep 29 (pp. 1-8). IEEE.
7. Tan X, Chen S, Zhou ZH, Zhang F. Face recognition from a single image per person: A survey. Pattern recognition. 2006 Sep 1;39(9):1725-45.
8. Yuan X, Park IK. Face de-occlusion using 3d morphable model and generative adversarial network. InProceedings of the IEEE/CVF International Conference on Computer Vision 2019 (pp. 10062-10071).
9. Chingovska, I, Nesli, E, André, A & Sébastien, M 2016, ‘Face Recognition Systems under Spoofing Attacks’, In Face Recognition across the Imaging Spectrum; Bourlai, T., Ed.; Springer: Berlin/Heidelberg, Germany, pp. 165-194
10. Feng, Litong, Lai-Man Po, Yuming Li, Xuyuan Xu, Fang Yuan Terence Chun-Ho Cheung & Kwok-Wai Cheung 2016, ‘Integration of image quality and motion cues for face anti-spoofing: A neural network approach’, Journal of Visual Communication and Image Representation, vol. 38 pp. 451-460.
11. Mei, L, Yang, D, Feng, Z & Lai, J 2015, ‘WLD-TOP Based algorithm against face spoofing attacks. In Biometric Recognition, Proceedings of the 10th Chinese Conference on Biometric Recognition.
12. Arashloo, SR, Kittler, J & Christmas, W 2015, ‘Face spoofing detection based on multiple descriptor fusion using multiscale dynamic binarized statistical image features’, IEEE Trans. Inf. Forensics Secur, vol. 10, pp. 2396-2407.
13. Boulkenafet, Z, Komulainen, J & Hadid, A 2015, ‘Face anti-spoofing based on color texture analysis’, in IEEE International Conference on Image Processing (ICIP2015)