Abstract
Recently, in the field of face recognition, deep learning has achieved great success. FaceNet, one of the Google’s deep learning frameworks, obtained nearly 100% accuracy in recognizing high-resolution faces. But, its performance on low-resolution images is unsatisfactory. Here, to justify the above statement, the performance of FaceNet has been evaluated on four well-known facial databases. For improving the performance, the face recognition algorithm for low-resolution images has been designed. Specifically, the algorithm performs image enhancement using a customized error back propagation network, and then the nearest patterns (NP) have been extracted and fed as embeddings to FaceNet. NP is a modified version of dual-cross patterns face descriptor that encodes the texture information of each image pixel in eight directions as unique features. The experimentation done on various databases such as LFW, ORL, EYB, and AR. The results of proposed approaches with NP have shown better performance than the other face descriptors like DCP, LBP, and LTP. Moreover, better results have been obtained on shrinking the Inception-Resnet-v1 network, which resulted in the fast convergence of the FaceNet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sharma P, Yadav RN, Arya KV (2014) Pose invariant face recognition using curvelet neural network. IET Biom 3(3):128–138
Turk Matthew, Pentland Alex (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86
Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041
Bartlett MS, Movellan JR, Sejnowski TJ (2002) Face recognition by independent component analysis. IEEE Trans Neural Netw 13(6):1450–1464
Sharma P, Arya KV, Yadav RN (2013) Efficient face recognition using generalized mean wavelet neural network. Signal Process 93(6):1557–1565. SCI Journal (impact factor 2.238)
Phillips PJ (1999) Support vector machines applied to face recognition. In: David AC (ed) Proceedings of the 1998 conference on advances in neural information processing systems II, 1999. MIT Press, Cambridge, MA, USA, pp 803–809
Sharma P, Arya KV, Yadav RN (2011) Extraction of facial features using higher order moments in curvelet transform and recognition using generalized mean neural networks. In: International conference on soft computing for problem solving at IIT Roorkee, vol 131, pp 717–728, 20–22 Dec 2011
Sharma P, Yadav RN, Arya KV (2016) Face recognition from video using generalized mean deep learning neural network. In: 2016 4th international symposium on computational and business intelligence (ISCBI). Olten, pp 195–199
Arya KV, Upadhyay G, Upadhyay S, Tiwari S, Sharma P (2016) Facial recognition using histogram of Gabor phase patterns and self organizing maps. In: 2016 11th international conference on industrial and information systems (ICIIS). Roorkee, pp 883–889
Ghazi MM, Ekenel HK (2016) A comprehensive analysis of deep learning based representation for face recognition. In: 2016 IEEE conference on computer vision and pattern recognition workshops (CVPRW). Las Vegas, NV, pp 102–109
Kurmi US, Agrawal D, Baghel RK (2014) Study of different face recognition algorithms and challenges. Int J Eng Res 3:112–115. https://doi.org/10.17950/ijer/v3s2/216
Li Z, Hou Y, Liu H, Li X (2014) Very low resolution face reconstruction based on multi-output regression. In: IEEE workshop on electronics, computer and applications. Ottawa, ON, pp 74–77
Shi J, Qi C (2015) From local geometry to global structure: learning latent subspace for low-resolution face image recognition. IEEE Signal Process Lett 22(5):554–558
Kaur R, Himanshi E (2015) Face recognition using principal component analysis. In: IEEE international advance computing conference (IACC). Bangalore, pp 585–589
Xu Y, Jin Z (2008) Down-sampling face images and low-resolution face recognition. In: 3rd international conference on innovative computing information and control. Dalian, Liaoning, pp 392–392
Raghavendra R, Raja KB, Yang B, Busch C (2013) Comparative evaluation of super-resolution techniques for multi-face recognition using light-field camera. In: 2013 18th international conference on digital signal processing (DSP). Fira, pp 1–6
Jia K, Gong SG (2005) Multi-modal tensor face for simultaneous super-resolution and recognition. In: Proceedings of IEEE 10th international conference on computer vision (ICCV), vol 2. Beijing, China, pp 1683–1690
Choi JY, Ro YM, Plataniotis KN (2009) Color face recognition for degraded face images. IEEE Trans Syst Man Cybern, Part B, Cybern 39(5):1217–1230
Biswas S, Bowyer KW, Flynn PJ (2012) Multidimensional scaling for matching low-resolution face images. IEEE Trans Pattern Anal Mach Intell 34(10):2019–2030
Ren CX, Dai DQ, Yan H (2012) Coupled kernel embedding for low-resolution face recognition. IEEE Trans Image Process 21(8):3770–3783
Tran CK, Lee TF, Tuan CC, Lu CH, Chao PJ (2013) Improving face recognition performance using similarity feature-based selection and classification algorithm. In: 2013 Second international conference on robot, vision and signal processing. Kitakyushu, pp 56–60
Ding C, Choi J, Tao D, Davis LS (2016) Multi-directional multi-level dual-cross patterns for robust face recognition. IEEE Trans Pattern Anal Mach Intell 38(3):518–531
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Golla, M.R., Sharma, P., Madarkar, J. (2020). Face Recognition Algorithm for Low-Resolution Images. In: Shukla, R., Agrawal, J., Sharma, S., Chaudhari, N., Shukla, K. (eds) Social Networking and Computational Intelligence. Lecture Notes in Networks and Systems, vol 100. Springer, Singapore. https://doi.org/10.1007/978-981-15-2071-6_29
Download citation
DOI: https://doi.org/10.1007/978-981-15-2071-6_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2070-9
Online ISBN: 978-981-15-2071-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)