The convolutional neural network, based on multi-scale features, is introduced to thermal infrared face identification in this paper. A novel CNN structure is proposed based on characteristics of thermal infrared faces. To enhance and extract inconspicuous thermal infrared facial features for identification, convoluted edges are taken as the initial features. A regional parallel structured CNN algorithm (RPS net) is proposed to obtain multi-scale features based on edge information. Extensive experiments are conducted and analyzed, including statistical test with various classifiers, feature vector property, accuracies of each class and robustness against various noise. The experimental result indicates that RPS net overtakes algorithms based on traditional features (HoG, Fisherface and LBP) and some CNN algorithms (Alex net, VGG net, DeepID net and TFR net), with high quality features. Therefore, RPS net is effective and robust for thermal infrared face identification.
RobertsLG. Machine perception of three-dimensional solids. Massachusetts Institute of Technology, 1963.
2.
SobelI. Neighborhood coding of binary images for fast contour following and general binary array processing. Computer Graphics & Image Processing1978; 8(1): 127-135.
3.
PrewittJ. Object enhancement and extraction. Picture Processing and Psychopictorics1970; 75-149.
4.
GhiassRS, et al. Infrared face recognition: A comprehensive review of methodologies and databases. Pattern Recognition2014; 47(9): 2807-2824.
5.
PapakostasGA, et al. Thermal infrared face recognition based on lattice computing (LC) techniques. IEEE International Conference on Fuzzy Systems (FUZZ)2013; 1-6.
6.
FarokhiS, et al. Near infrared face recognition using Zernike moments and Hermite kernels. Information Sciences2015; 316: 234-245.
7.
LiuL, et al. Toward large-population face identification in unconstrained videos. IEEE Transactions on Circuits and Systems for Video Technology2014; 24(11): 1874-1884.
8.
LencLKrálP. Local binary pattern based face recognition with automatically detected fiducial points. Integrated Computer-Aided Engineering2016; 23(2): 129-139.
9.
TranQDKantartzisPLiatsisP. Improving fusion with optimal weight selection in face recognition. Integrated Computer-Aided Engineering2012; 19(3): 229-237.
10.
LiZ, et al. Learning compact feature descriptor and adaptive matching framework for face recognition. IEEE Transactions on Image Processing2015; 24(9): 2736-2745.
11.
CoverTHartP. Nearest neighbor pattern classification. IEEE Transactions on Information Theory1967; 13(1): 21-27.
12.
HintonG, et al. Reducing the dimensionality of data with neural networks. Science2006; 313(5786): 504-507.
13.
LongJShelhamerEDarrellT. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2015; 3431-3440.
14.
ChenL, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv preprint arXiv: 1606.00915, 2016.
15.
LiuW, et al. SSD: Single shot multibox detector. European Conference on Computer Vision2016; 21-37.
16.
HeK, et al. Mask r-cnn. arXiv preprint arXiv: 1703.06870, 2017.
17.
LinYNieZMaH. Structural damage detection with automatic feature-extraction through Deep Learning. Computer-Aided Civil and Infrastructure Engineering, 2017.
18.
RafieiMHAdeliH. A novel machine learnin-based algorithm to detect damage in high-rise building structures. The Structural Design of Tall and Special Buildings2017; 26(18).
19.
RafieiMHKhushefatiWHDemirbogaR, et al. Supervised Deep Restricted Boltzmann Machine for Estimation of Concrete. ACI Materials Journal2017; 114(2).
20.
ChenLHuXXuT, et al. Turn signal detection during nighttime by CNN detector and perceptual hashing tracking. IEEE Transactions on Intelligent Transportation Systems, 2017.
21.
LiaoTY. On-line Vehicle Routing Problems for Carbon Emissions Reduction. Computer-Aided Civil and Infrastructure Engineering, 2017.
22.
Ortega-ZamoranoFJerezJMGómezI, et al. Layer multiplexing FPGA implementation for deep back-propagation learning. Integrated Computer-Aided Engineering2017; 24(2): 171-185.
23.
KoziarskiMCyganekB. Image recognition with deep neural networks in presence of noise-Dealing with and taking advantage of distortions. Integrated Computer-Aided Engineering2017; 24(4): 337-349.
24.
TaigmanY, et al. Deepface: Closing the gap to human-level performance in face verification. IEEE Conference on Computer Vision and Pattern Recognition2014; 1701-1708.
25.
SunY, et al. Deep Learning face representation by joint identification-verification. Advances in Neural Information Processing Systems2014; 1988-1996.
26.
SunY, et al. Deep Learning face representation from predicting 10,000 classes. IEEE Conference on Computer Vision and Pattern Recognition2014; 1891-1898.
27.
ZhuZ, et al. Deep Learning identity-preserving face space. IEEE International Conference on Computer Vision2013; 113-120.
28.
XiongC, et al. Convolutional fusion network for face verification in the wild. IEEE Transactions on Circuits and Systems for Video Technology2016; 26(3): 517-528.
29.
LuJ, et al. Reconstruction-based metric learning for unconstrained face verification. IEEE Transactions on Information Forensics and Security2015; 10(1): 79-89.
30.
ChenJC, et al. Unconstrained face verification using deep cnn features. IEEE Winter Conference on Applications of Computer Vision2016; 1-9.
31.
XiongC, et al. Convolutional fusion network for face verification in the wild. IEEE Transactions on Circuits and Systems for Video Technology2016; 26(3): 517-528.
32.
SunY, et al. Deepid3: Face recognition with very deep neural networks. arXiv preprint arXiv: 1502.00873, 2015.
33.
WuZPengMChenT. Thermal face recognition using convolutional neural network. IEEE International Conference on Optoelectronics and Image Processing2016; 6-9.
34.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 1409.1556, 2014.
35.
SzegedyC, et al. Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition2015; 1-9.
36.
DalalN, et al. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition2005; 886-893.
37.
OjalaT, et al. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence2002; 24(7): 971-987.
38.
ScholkopftBMullertKR. Fisher discriminant analysis with kernels. Neural Networks for Signal Processing IX1999; 1(1): 1.
39.
ZhangJ, et al. Face recognition: Eigenface, elastic matching, and neural nets. Proceedings of the IEEE1997; 85(9): 1423-1435.
40.
GunturkBK, et al. Eigenface-domain super-resolution for face recognition. IEEE Transactions on Image Processing2003; 12(5): 597-606.
BaiXWangPZhouF. Pedestrian segmentation in infrared images based on circular shortest path. IEEE Transactions on Intelligent Transportation Systems2016; 17(8): 2214-2222.
43.
BaiXWangYLiuH, et al. Symmetry information based fuzzy clustering for infrared pedestrian segmentation. IEEE Transactions on Fuzzy Systems, 2017.
44.
KrizhevskyASutskeverIHintonGE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems2012; 1097-1105.
45.
HintonGE, et al. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv: 1207.0580, 2012.
46.
OTCBVS homepage on the Internet. IRIS Thermal/Visible Face Database; 2017 cited 3 Nov 2017. Available from: http://vcipl-okstate.org/pbvs/bench/Data/02/download.html
47.
OTCBVS homepage on the Internet. Terravic Facial IR Database; 2017 cited 3 Nov 2017. Available from: http://vcipl-okstate.org/pbvs/bench/Data/04/download.html
48.
JiaYShelhamerEDonahueJ, et al. Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM International Conference on Multimedia2014; 1: 675-678.
49.
ChenD, et al. Bayesian face revisited: A joint formulation. European Conference on Computer Vision2012; 566-579.
50.
ChangCC, et al. LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems & Technology2006; 2(3): 389-396.
51.
BreimanL. Random forests. Machine Learning2001; 45(1):5-32.
ParkHSAdeliH. Distributed neural dynamics algorithms for optimization of large steel structures. Journal of Structural Engineering1997; 123(7): 880-888.
54.
AdeliH. Supercomputing in Engineering Analysis. Marcel Dekker, New York, 1992.
55.
AdeliH. Parallel Processing in Computational Mechanics. Marcel Dekker, New York, 1992.
