Image processing effects on the deep face recognition system

Jinhua Zeng; Xiulian Qiu; Shaopei Shi; Jinhua Zeng; Xiulian Qiu; Shaopei Shi

doi:10.3934/mbe.2021064

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 2: 1187-1200. doi: 10.3934/mbe.2021064

Previous Article Next Article

Research article Special Issues

Image processing effects on the deep face recognition system

1.
Academy of Forensic Science, China
2.
China East China University of Political Science and Law, China

Received: 09 September 2020 Accepted: 03 January 2021 Published: 13 January 2021

Face recognition technology has become an important quantitative examination method in the field of forensic identification of human images. However, face image quality affects the recognition performance of face recognition systems. Existing research on the effects of face image denoising and enhancement methods on the face recognition performance are typically based on facial images with manually synthesized noises rather than the noises under natural environmental corruption, and their studied face recognition techniques are limited on the traditional face recognition algorithms rather than state-of-the-art convolutional neural network based face recognition methods. In this work, face image materials from 33 real cases in forensic identification of human images were collected for quantitative analysis of the effects of face image denoising and enhancement methods on the deep face recognition performance of the MXNet system architecture based face recognition system. The results show that face image quality has a significant effect on the recognition performance of the face recognition system, and the image processing techniques can enhance the quality of face images, and then improve the recognition precision of the face recognition system. In addition, the effects of the Gaussian filtering are better than the self-snake model based image enhancement method, which indicates that the image denoising methods are more suitable for performance improvement of the deep face recognition system rather than the image enhancement techniques under the application of the practical cases.
- face recognition,
- image enhancement,
- image denoising,
- forensic identification of human images,
- MXNet
Citation: Jinhua Zeng, Xiulian Qiu, Shaopei Shi. Image processing effects on the deep face recognition system[J]. Mathematical Biosciences and Engineering, 2021, 18(2): 1187-1200. doi: 10.3934/mbe.2021064

Related Papers:

Abstract

Face recognition technology has become an important quantitative examination method in the field of forensic identification of human images. However, face image quality affects the recognition performance of face recognition systems. Existing research on the effects of face image denoising and enhancement methods on the face recognition performance are typically based on facial images with manually synthesized noises rather than the noises under natural environmental corruption, and their studied face recognition techniques are limited on the traditional face recognition algorithms rather than state-of-the-art convolutional neural network based face recognition methods. In this work, face image materials from 33 real cases in forensic identification of human images were collected for quantitative analysis of the effects of face image denoising and enhancement methods on the deep face recognition performance of the MXNet system architecture based face recognition system. The results show that face image quality has a significant effect on the recognition performance of the face recognition system, and the image processing techniques can enhance the quality of face images, and then improve the recognition precision of the face recognition system. In addition, the effects of the Gaussian filtering are better than the self-snake model based image enhancement method, which indicates that the image denoising methods are more suitable for performance improvement of the deep face recognition system rather than the image enhancement techniques under the application of the practical cases.

References

[1]	U. Scherhag, C. Rathgeb, J. Merkle, R. Breithaupt, C. Busch, Face recognition systems under morphing attacks: A survey, IEEE Access, 7 (2019), 23012–23026. doi: 10.1109/ACCESS.2019.2899367
[2]	A. Fydanaki, Z. Geradts, Evaluating OpenFace: an open-source automatic facial comparison algorithm for forensics, Forensic Sci. Res., 3 (2018), 202–209. doi: 10.1080/20961790.2018.1523703
[3]	M. P. Evison, R. W. V. Bruegge, The magna database: A database of three-dimensional facial images for research in human identification and recognition, Forensic Sci. Commun., 10 (2008), 1–11.
[4]	J. Zeng, S. Shi, Q. Lu, Y. Li, X. Qiu, Face recognition techniques for forensic identification of human images, Int. J. Digital Content Technol. Its Appl., 11 (2017), 34–43.
[5]	J. Han, B. Bhanu, Individual recognition using gait energy image, IEEE Trans. Pattern Anal. Mach. Intell., 28 (2006), 316–322. doi: 10.1109/TPAMI.2006.38
[6]	S. Bharadwaj, H. Bhatt, M. Vatsa, R. Singh, A. Noore, Quality assessment based denoising to improve face recognition performance, CVPR 2011 WORKSHOPS, Colorado Springs, CO, 2011,140–145.
[7]	A. A. Dawood, M. F. Saleh, Review of different techniques for image denoising, Int. J. Innovative Res. Comput. Commun. Eng., 6 (2018), 2498–2505.
[8]	L. Fan, F. Zhang, H. Fan, C. Zhang, Brief review of image denoising techniques, Visual Comput. Ind. Biomed. Art, 2 (2019), 7. doi: 10.1186/s42492-019-0016-7
[9]	P. Janani, J. Premaladha, K. S. Ravichandran, Image enhancement techniques: A study, Indian J. Sci. Technol., 8 (2015), 125–145. doi: 10.17485/ijst/2015/v8iS6/71216
[10]	G. Deng, L. W. Cahill, An adaptive Gaussian filtering for noise reduction and edge detection, Nuclear Science Symposium and Medical Imaging Conference, 3 (1993), 1615–1619.
[11]	X. Jia, S. Liu, X. Feng,, L. Zhang, FOCNet: A fractional optimal control network for image denoising, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Available from: https://ieeexplore.ieee.org/document/8954104.
[12]	C. Tian, Y. Xu, L. Fei, K. Yan, Deep learning for image denoising: a survey, International Conference on Genetic and Evolutionary Computing, 384 (2019), 563–572.
[13]	C. Knaus, M. Zwicker, Progressive image denoising, IEEE Trans. Image Process., 23 (2014), 3114–3125. doi: 10.1109/TIP.2014.2326771
[14]	S. Cha, T. Moon, Fully convolutional pixel adaptive image denoiser, 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, 4160–4169.
[15]	J. Xu, L. Zhang, D. Zhang, A trilateral weighted sparse coding scheme for real-world image denoising, The European Conference on Computer Vision (ECCV), 2018, 20–36.
[16]	R. Wang, X. Xiao, B. Guo, Q. Qin, R. Chen, An effective image denoising method for UAV images via improved generative adversarial networks, Sensors, 18 (2018), 1985.
[17]	M. Diwakar, M. Kumar, A review on CT image noise and its denoising, Biomed. Signal Process. Control, 42 (2018), 73–88. doi: 10.1016/j.bspc.2018.01.010
[18]	J. Benesty, J. D. Chen, Y. T. Huang, Study of the widely linear wiener filter for noise reduction, IEEE International Conference on Acoustics, Speech, and Signal Processing, Dallas, Texas, USA, 2010,205–208.
[19]	S. G. Mallat, A theory for multiresolution signal decomposition: the wavelet representation, IEEE Trans. Pattern. Anal. Mach. Intell., 11 (1989), 674–693. doi: 10.1109/34.192463
[20]	W. Zhang, R. Li, K. He, J. Zhou, Approach to image denoising and enhancement based on 3DDCT, J. Univ. Electron. Sci. Technol. China, 40 (2011), 742–746.
[21]	T. Yan, M. Qu, C. Zhou, Image denoising with BEMD and edge-preserving self-snake model, International Conference on Intelligent Computing, 8588 (2014), 435–442.
[22]	K. Nguyen, C. Fookes, S. Sridharan, M. Tistarelli, M. Nixon, Super-resolution for biometrics: A comprehensive survey, Pattern Recognit., 78 (2018), 23–42. doi: 10.1016/j.patcog.2018.01.002
[23]	J. Jiang, J. Ma, C. Chen, X. Jiang, Z. Wang, Noise robust face image super-resolution through smooth sparse representation, IEEE Trans. Cybernetics, 47 (2016), 3991–4002.
[24]	R. Tkachenko, P. Tkachenko, I. Izonin, Y. Tsymbal, Learning-based image scaling using neural-like structure of geometric transformation paradigm, in Advances in Soft Computing and Machine Learning in Image Processing, (2018), 537–565.
[25]	I. Izonin, R. Tkachenko, D. Peleshko, T. Rak, D. Batyuk, Learning-based image super-resolution using weight coefficients of synaptic connections, 2015 Xth International Scientific and Technical Conference "Computer Sciences and Information Technologies" (CSIT), 2015, 25–29.
[26]	Y. Rashkevych, D. Peleshko, O. Vynokurova, I. Izonin, N. Lotoshynska, Single-frame image super-resolution based on singular square matrix operator, 2017 IEEE First Ukraine Conference on Electrical and Computer Engineering, 2017,944–948.
[27]	M. Emambakhsh, J. Gao, A.N. Evans, An evaluation of denoising algorithms for 3D face recognition, 5th International Conference on Imaging for Crime Detection and Prevention, London, 2013.
[28]	L. Zhang, L. Zhang, L. Li, Illumination quality assessment for face images: A benchmark and a convolutional neural networks based model, in International Conference on Neural Information Processing, Springer, Cham, 2017,583–593.
[29]	N. Zhuang, Q. Zhang, C. Pan, B. Ni, Y. Xu, X. Yang, W. Zhang, Recognition oriented facial image quality assessment via deep convolutional neural network, Neurocomputing, 358 (2019), 109–118. doi: 10.1016/j.neucom.2019.04.057
[30]	J. Yu, K. Sun, F. Gao, S. Zhu, Face biometric quality assessment via light CNN, Pattern Recog. Lett., 107 (2018), 25–32. doi: 10.1016/j.patrec.2017.07.015
[31]	V. V. Starovoitov, D. I. Samal, D. V. Briliuk, Image enhancement for face recognition, International Conference on Iconics, St. Petersburg, Russia, 2003.
[32]	T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray-scale and rotation invariant texture classification with local binary patterns, IEEE Trans. Pattern Anal. Mach. Intell., 24 (2002), 971–987. doi: 10.1109/TPAMI.2002.1017623
[33]	S. Chang, B. Yu, M. Vetterli, Adaptive wavelet thresholding for image denoising and compression, IEEE Trans. Image Process., 9 (2000), 1532–1546. doi: 10.1109/83.862633
[34]	D. Andrews, C. Mallows, Scale mixtures of normal distributions, J. Royal Stat. Soc., 36 (1974), 99–102.
[35]	A. Martinez, R. Benevento, The AR face database, CVC Technical Report #24, 1998.
[36]	P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, et al., Overview of the face recognition grand challenge, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 1(2005), 947–954. doi: 10.1109/CVPR.2005.268
[37]	S. Mittal, S. Agarwal, M. J. Nigam, Real time multiple face recognition: A deep learning approach, Proceedings of the 2018 International Conference on Digital Medicine and Image Processing, 2018, 70–76.
[38]	I. Masi, Y. Wu, T. Hassner, P. Natarajan, Deep face recognition: A survey, 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2018. Available from: https://ieeexplore.ieee.org/document/8614364.
[39]	G. Gilboa, N. Sochen, Y. Y. Zeevi, Image enhancement and denoising by complex diffusion process, IEEE Trans. Patt. Anal. Mach. Intell., 26 (2004), 1020–1036. doi: 10.1109/TPAMI.2004.47
[40]	P. Perona, J. Malik, Scale space and edge detection using anisotropic diffusion, IEEE Trans. Pattern Anal. Mach. Intell., 12 (1990), 629–639. doi: 10.1109/34.56205

Reader Comments

your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)