An efficient deep learning model for classification of thermal face images

PurposeThe objective of this paper is to perform infrared (IR) face recognition efficiently with convolutional neural networks (CNNs). The proposed model in this paper has several advantages such as the automatic feature extraction using convolutional and pooling layers and the ability to distinguish between faces without visual details.Design/methodology/approachA model which comprises five convolutional layers in addition to five max-pooling layers is introduced for the recognition of IR faces.FindingsThe experimental results and analysis reveal high recognition rates of IR faces with the proposed model.Originality/valueA designed CNN model is presented for IR face recognition. Both the feature extraction and classification tasks are incorporated into this model. The problems of low contrast and absence of details in IR images are overcome with the proposed model. The recognition accuracy reaches 100% in experiments on the Terravic Facial IR Database (TFIRDB).

[1]  Xinzhu Yang,et al.  Power-aware Regions-of-Interest Computational Resource Allocation for Mobile Sign Language Video Encoding , 2013 .

[2]  Hassan Ugail,et al.  Deep face recognition using imperfect facial data , 2019, Future Gener. Comput. Syst..

[3]  X. Niu,et al.  An Enhanced Algorithm for Thermal Face Recognition , 2013 .

[4]  Ahmed A. Abd El-Latif,et al.  An enhanced thermal face recognition method based on multiscale complex fusion for Gabor coefficients , 2013, Multimedia Tools and Applications.

[5]  Xuehu Yan,et al.  A novel template protection scheme for multibiometrics based on fuzzy commitment and chaotic system , 2015, Signal Image Video Process..

[6]  Chalavadi Krishna Mohan,et al.  Human action recognition in RGB-D videos using motion sequence information and deep learning , 2017, Pattern Recognit..

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  Ahmed A. Abd El-Latif,et al.  Two-directional two-dimensional modified Fisher principal component analysis: an efficient approach for thermal face verification , 2013, J. Electronic Imaging.

[10]  Sergio Escalera,et al.  RGB-D-based Human Motion Recognition with Deep Learning: A Survey , 2017, Comput. Vis. Image Underst..

[11]  Ba Tuan Le,et al.  Coal analysis based on visible-infrared spectroscopy and a deep neural network , 2018, Infrared Physics & Technology.

[12]  Yang Li,et al.  Ship detection in spaceborne infrared images based on Convolutional Neural Networks and synthetic targets , 2019, Infrared Physics & Technology.

[13]  Bin Sheng,et al.  Deep gesture interaction for augmented anatomy learning , 2019, Int. J. Inf. Manag..

[14]  Da Liu,et al.  Emotional image color transfer via deep learning , 2018, Pattern Recognit. Lett..

[15]  K Nishanth.  Identification of Diabetic Maculopathy Stages using Fundus Images , 2015 .

[16]  E. Erçelebi,et al.  The use of infrared thermal imaging in the diagnosis of deep vein thrombosis , 2017 .

[17]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Min Peng,et al.  Thermal face recognition using convolutional neural network , 2016, 2016 International Conference on Optoelectronics and Image Processing (ICOIP).

[19]  Ahmed A. Abd El-Latif,et al.  Multibiometric Complex Fusion for Visible and Thermal Face Images , 2013 .

[20]  Xuehu Yan,et al.  A Novel Hybrid Multibiometrics Based on the Fusion of Dual Iris, Visible and Thermal Face Images , 2013, 2013 International Symposium on Biometrics and Security Technologies.

[21]  Yang Lei,et al.  Visible and infrared image fusion using NSST and deep Boltzmann machine , 2018 .

[22]  Qian Chen,et al.  Single infrared image enhancement using a deep convolutional neural network , 2019, Neurocomputing.

[23]  Ripul Ghosh,et al.  Deep learning approach for human action recognition in infrared images , 2018, Cognitive Systems Research.

[24]  Han Huang,et al.  Deep infrared pedestrian classification based on automatic image matting , 2019, Appl. Soft Comput..