Abstract

In this Paper, study on Independent Component Analysis (ICA) with ConvolutionalNeural Networks (CNNs). ICA is employed to extract statistically independent features from facial images, which are then used as inputs for a deep CNN architecture. ICA is a powerful statistical technique used in various fields, including signal processing and computer vision. Experimental results demonstrate the superior performance of this fusion approach compared to traditional methods. This paper discusses the implications of this methodology for real-world applications and its potential to transform the field of computer vision.

Author

Raghvendra Singh   ( Pages 11-20 )
Email:rsingh@uprtou.ac.in
Affiliation:School of Sciences, UP Rajarshi Tandon Open University Prayagraj, UP, India       DOI: https://doi.org/10.58517/IJSE.2023.2102

Keyword

ICA, Convolutional, CNN

References

1. Zhao, Wenyi, Rama Chellappa, P. Jonathon Phillips, and Azriel Rosenfeld. "Face recognition: A literature survey." ACM computing surveys (CSUR) 35, no. 4 (2003): 399-458.
2. Hyvarinen, J. Karhunen and E. Oja, “Independent Component Analysis,” Wiley, New York, 2001.
3. CoÅŸkun, Musab, AyÅŸegül Uçar, Özal Yildirim, and Yakup Demir. "Face recognition based on convolutional neural network." In 2017 International Conference on Modern Electrical and Energy Systems (MEES), pp. 376-379. IEEE, 2017.
4. Hu, Guosheng, Yongxin Yang, Dong Yi, Josef Kittler, William Christmas, Stan Z. Li, and Timothy Hospedales. "When face recognition meets with deep learning: an evaluation of convolutional neural networks for face recognition." In Proceedings of the IEEE international conference on computer vision workshops, pp. 142-150. 2015.
5. Karahan, Samil, Merve Kilinc Yildirum, Kadir Kirtac, Ferhat Sukru Rende, Gultekin Butun, and Hazim Kemal Ekenel. "How image degradations affect deep cnn-based face recognition?." In 2016 international conference of the biometrics special interest group (BIOSIG), pp. 1-5. IEEE, 2016.
6. H. Attias and C. E. Schreiner, “Blind source separation and deconvol.ution: the dynamic component analysis algorithm,” Neural Computing, vol. 10, no. 6, pp. 1373–1424, 1998.
7. J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.. 15, no. 11, pp. 1148–1161, 1993.
8. Bartlett, Marian Stewart, Javier R. Movellan, and Terrence J. Sejnowski. "Face recognition by independent component analysis." IEEE Transactions on neural networks 13, no. 6 (2002): 1450-1464.
9. Liu, Chengjun, and Harry Wechsler. "Independent component analysis of Gabor features for face recognition." IEEE transactions on Neural Networks 14, no. 4 (2003): 919-928.
10. Sakthivel, S., and R. Lakshmipathi. "Enhancing face recognition using improved dimensionality reduction and feature extraction algorithms–an evaluation with ORL database." International Journal of Engineering Science and Technology 2, no. 6 (2010): 2288-2295.
11. Shukla, A., Shukla, A., Singh, R. “Neural networks based face recognition system for biometric security” Indian journal of Engineering, ISSN 2319–7757|May 2023, PP 1-9.
12. Singh, R, Pathak., P.N ‘‘Mathematical Modelling in Neural Network’s’’ The Journal of Oriental Research Madras, ISSN: 0022-3301: May 2022, PP 162-173.
13. Shukla, A., Shukla, A., Singh, R ‘‘Mathematical Modeling For Attendance Marking Face Recognition System” Neuro Quantology Indisciplinary Jouranal, ISSN: 3328-3350, December 2022, PP 1-23.