{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:20Z","timestamp":1775578760395,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2018,6,28]],"date-time":"2018-06-28T00:00:00Z","timestamp":1530144000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701046"],"award-info":[{"award-number":["61701046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Given that facial features contain a wide range of identification information and cannot be completely represented by a single feature, the fusion of multiple features is particularly significant for achieving a robust face recognition performance, especially when there is a big difference between the test sets and the training sets. This has been proven in both traditional and deep learning approaches. In this work, we proposed a novel method named C2D-CNN (color 2-dimensional principal component analysis (2DPCA)-convolutional neural network). C2D-CNN combines the features learnt from the original pixels with the image representation learnt by CNN, and then makes decision-level fusion, which can significantly improve the performance of face recognition. Furthermore, a new CNN model is proposed: firstly, we introduce a normalization layer in CNN to speed up the network convergence and shorten the training time. Secondly, the layered activation function is introduced to make the activation function adaptive to the normalized data. Finally, probabilistic max-pooling is applied so that the feature information is preserved to the maximum extent while maintaining feature invariance. Experimental results show that compared with the state-of-the-art method, our method shows better performance and solves low recognition accuracy caused by the difference between test and training datasets.<\/jats:p>","DOI":"10.3390\/s18072080","type":"journal-article","created":{"date-parts":[[2018,6,28]],"date-time":"2018-06-28T10:53:33Z","timestamp":1530183213000},"page":"2080","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Robust Face Recognition Using the Deep C2D-CNN Model Based on Decision-Level Fusion"],"prefix":"10.3390","volume":"18","author":[{"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronic and Information, Yangtze University, Jingzhou 434023, China"},{"name":"National Demonstration Center for Experimental Electrical and Electronic Education, Yangtze University, Jingzhou 434023, China"}]},{"given":"Tao","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"}]},{"given":"Chang","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"}]},{"given":"Kai","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Yangtze University, Jingzhou 434023, China"},{"name":"National Demonstration Center for Experimental Electrical and Electronic Education, Yangtze University, Jingzhou 434023, China"}]},{"given":"Fang-Qing","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Yangtze University, Jingzhou 434023, China"},{"name":"National Demonstration Center for Experimental Electrical and Electronic Education, Yangtze University, Jingzhou 434023, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,6,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1016\/j.patrec.2006.12.018","article-title":"2D and 3D face recognition: A survey","volume":"28","author":"Abate","year":"2007","journal-title":"Pattern Recognit. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kim, D.J., Sohn, M.K., and Kim, H. (2014, January 18\u201320). Geometric Feature-Based Face Normalization for Facial Expression Recognition. Proceedings of the 2nd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS), Madrid, Spain.","DOI":"10.1109\/AIMS.2014.52"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ouarda, W., Trichili, H., and Alimi, A.M. (2014, January 11\u201314). Face recognition based on geometric features using Support Vector Machines. Proceedings of the 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR), Tunis, Tunisia.","DOI":"10.1109\/SOCPAR.2014.7007987"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wei, M., and Ma, B. (2015, January 9\u201311). Face Recognition Based on Randomized Subspace Feature. Proceedings of the 27th International Conference on Tools with Artificial Intelligence (ICTAI), Vietri sul Mare, Italy.","DOI":"10.1109\/ICTAI.2015.101"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.inffus.2015.09.005","article-title":"An ensemble of patch-based subspaces for makeup-robust face recognition","volume":"32","author":"Chen","year":"2016","journal-title":"Inf. Fusion"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hanmandlu, M., Gupta, D., and Vasikarla, S. (2013, January 23\u201325). Face recognition using Elastic bunch graph matching. Proceedings of the IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA.","DOI":"10.1109\/AIPR.2013.6749338"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, C., Dong, F., and Zhou, Z. (2013, January 6\u201310). Parallelization of elastic bunch graph matching (EBGM) algorithm for fast face recognition. Proceedings of the IEEE China Summit & International Conference on Signal and Information Processing, Beijing, China.","DOI":"10.1109\/ChinaSIP.2013.6625328"},{"key":"ref_8","unstructured":"Wan, L., Liu, N., Huo, H., and Fang, T. (2017, January 2\u20134). Face Recognition with Convolutional Neural Networks and subspace learning. Proceedings of the 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdu, China."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Qi, X., Liu, C., and Schuckers, S. (2018, January 11\u201312). CNN based key frame extraction for face in video recognition. Proceedings of the IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA), Singapore.","DOI":"10.1109\/ISBA.2018.8311477"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.image.2017.05.004","article-title":"Pose-invariant 3D face recognition using half face","volume":"57","author":"Liang","year":"2017","journal-title":"Signal Process. Image Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1016\/j.neucom.2017.09.070","article-title":"Expression-insensitive 3D face recognition by the fusion of multiple subject-specific curves","volume":"275","author":"Li","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Dagnes, N., Vezzetti, E., Marcolin, F., and Tornincasa, S. (2018). Occlusion detection and restoration techniques for 3D face recognition: A literature review. Mach. Vis. Appl., 1\u201325.","DOI":"10.1007\/s00138-018-0933-z"},{"key":"ref_13","first-page":"1","article-title":"3D geometry-based automatic landmark localization in presence of facial occlusions","volume":"14","author":"Vezzetti","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12008-014-0244-1","article-title":"Cleft lip pathology diagnosis and foetal landmark extraction via 3D geometrical analysis","volume":"11","author":"Moos","year":"2017","journal-title":"Int. J. Interact. Des. Manuf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"053028","DOI":"10.1117\/1.JEI.24.5.053028","article-title":"Face recognition across makeup and plastic surgery from real-world images","volume":"24","author":"Moeini","year":"2015","journal-title":"J. Electron. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.fss.2017.06.002","article-title":"Fuzzy interval-valued multi criteria based decision making for ranking features in multi-modal 3D face recognition","volume":"337","author":"Ramalingam","year":"2018","journal-title":"Fuzzy Sets Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Abbad, A., Abbad, K., and Tairi, H. (2017). 3D face recognition: Multi-scale strategy based on geometric and local descriptors. Comput. Electr. Eng.","DOI":"10.1016\/j.compeleceng.2017.08.017"},{"key":"ref_18","unstructured":"Kim, J., Han, D., Hwang, W., and Kim, J. (July, January 28). 3D face recognition via discriminative keypoint selection. Proceedings of the 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Jeju, Korea."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Soltanpour, S., Wu, Q.J., and Anvaripour, M. (2015, January 15\u201317). Multimodal 2D-3D face recognition using structural context and pyramidal shape index. Proceedings of the 6th International Conference on Imaging for Crime Prevention and Detection (ICDP), London, UK.","DOI":"10.1049\/ic.2015.0100"},{"key":"ref_20","unstructured":"Wang, X., Ly, V., Guo, R., and Kambhamettu, C. (2014, January 5\u20138). 2D-3D face recognition via restricted boltzmann machines. Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP), Lisbon, Portugal."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, X., Ly, V., Guo, G., and Kambhamettu, C. (2013, January 9\u201311). A new approach for 2d-3d heterogeneous face recognition. Proceedings of the IEEE International Symposium on Multimedia (ISM), Anaheim, CA, USA.","DOI":"10.1109\/ISM.2013.58"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.cviu.2016.04.012","article-title":"3D-2D face recognition with pose and illumination normalization","volume":"154","author":"Kakadiaris","year":"2017","journal-title":"Comput. Vision Image Underst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C., He, K., and Tang, X. (2014, January 6\u201312). Learning a deep convolutional network for image super-resolution. Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Swiss.","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cai, H., Yan, F., and Mikolajczyk, K. (2010, January 13\u201318). Learning weights for codebook in image classification and retrieval. Proceedings of the Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5539918"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chaib, S., Yao, H., Gu, Y., and Amrani, M. (2017, January 19\u201322). Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models. Proceedings of the Ninth International Conference on Digital Image Processing (ICDIP), Hongkong, China.","DOI":"10.1117\/12.2281755"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., Ma, X., and Song, R. (2017). Facial Expression Recognition with Fusion Features Extracted from Salient Facial Areas. Sensors, 17.","DOI":"10.20944\/preprints201701.0102.v1"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4042","DOI":"10.1109\/TIP.2017.2713940","article-title":"Simultaneous feature and dictionary learning for image set based face recognition","volume":"26","author":"Lu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TIP.2017.2756450","article-title":"Frankenstein: Learning deep face representations using small data","volume":"27","author":"Hu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., and Laptev, I. (2014, January 24\u201327). Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks. Proceedings of the Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Masi, I., Tr\u1ea7n, A.T., Hassner, T., L-eksut, J.T., and Medioni, G. (2016, January 8\u201316). Do we really need to collect millions of faces for effective face recognition?. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46454-1_35"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.imavis.2017.01.011","article-title":"From pixels to sentiment: Fine-tuning cnns for visual sentiment prediction","volume":"65","author":"Campos","year":"2017","journal-title":"Image Vis. Comput."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nagori, V. (2016, January 14\u201317). Fine tuning the parameters of back propagation algorithm for optimum learning performance. Proceedings of the 2nd International Conference on contemporary Computing and Informatics, Noida, India.","DOI":"10.1109\/IC3I.2016.7917926"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Tzelepi, M., and Tefas, A. (2016, January 4\u20138). Exploiting supervised learning for finetuning deep CNNs in content based image retrieval. Proceedings of the 23rd International Conference on the Pattern Recognition (ICPR), Cancun, Mexico.","DOI":"10.1109\/ICPR.2016.7900080"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.patcog.2016.10.019","article-title":"Hyperspectral image reconstruction by deep convolutional neural network for classification","volume":"63","author":"Li","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Comput."},{"key":"ref_38","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"Glorot","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","unstructured":"Shang, W., Sohn, K., Almeida, D., and Lee, H. (2016, January 19\u201324). Understanding and improving convolutional neural networks via concatenated rectified linear units. Proceedings of the International Conference on Machine Learning (ICML), New York, NY, USA."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_41","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International conference on machine learning (ICML), Lille, France."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1109\/TIP.2011.2168413","article-title":"Color local texture features for color face recognition","volume":"21","author":"Choi","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lu, Z., Jiang, X., and Kot, A. (2017, January 5\u20139). A novel LBP-based Color descriptor for face recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952478"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Lu, Z., Jiang, X., and Kot, A. (2016, January 20\u201325). An effective color space for face recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.","DOI":"10.1109\/ICASSP.2016.7472031"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1109\/LSP.2015.2438024","article-title":"A Color Channel Fusion Approach for Face Recognition","volume":"22","author":"Lu","year":"2015","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.neucom.2017.06.070","article-title":"Adaptive activation functions in convolutional neural networks","volume":"272","author":"Qian","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Lee, H., Grosse, R., Ranganath, R., and Ng, A.Y. (2009, January 14\u201318). Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.","DOI":"10.1145\/1553374.1553453"},{"key":"ref_48","unstructured":"Beigy, H., and Meybodi, M.R. (2000, January 22\u201325). Adaptation of Parameters of BP Algorithm Using Learning Automata. Proceedings of the Sixth Brazilian Symposium on Neural Networks, Rio de Janeiro, Brazil."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1007\/s00521-005-0467-y","article-title":"Revisiting squared-error and cross-entropy functions for training neural network classifiers","volume":"14","author":"Kline","year":"2005","journal-title":"Neural Comput. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TSMCB.2009.2035629","article-title":"L1-norm-based 2DPCA","volume":"40","author":"Xuelong","year":"2010","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TAC.1981.1102568","article-title":"Principal component analysis in linear systems: Controllability, observability, and model reduction","volume":"26","author":"Moore","year":"1981","journal-title":"IEEE Trans. Autom. Cont."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.neucom.2014.10.074","article-title":"Color face recognition by PCA-like approach","volume":"152","author":"Xinguang","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Saxena, S., and Verbeek, J. (2016, January 8\u201316). Heterogeneous face recognition with CNNs. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-49409-8_40"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.sigpro.2017.10.024","article-title":"Feature fusion with covariance matrix regularization in face recognition","volume":"144","author":"Lu","year":"2018","journal-title":"Signal Process."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/j.patrec.2004.01.011","article-title":"Distance measures for PCA-based face recognition","volume":"25","author":"Perlibakas","year":"2004","journal-title":"Pattern Recognit. Lett."},{"key":"ref_56","unstructured":"Xu, A., Jin, X., Jiang, Y., and Guo, P. (2006, January 20\u201324). Complete two-dimensional PCA for face recognition. Proceedings of the 18th International Conference on Pattern Recognition (ICPR), Hong Kong, China."},{"key":"ref_57","unstructured":"Huang, G.B., Ramesh, M., Berg, T., and Learned-Miller, E. (2007). Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments, University of Massachusetts. No. 2. Technical Report 07-49."},{"key":"ref_58","unstructured":"Phillips, P.J., Flynn, P.J., and Scruggs, T. (2005, January 20\u201326). Overview of the Face Recognition Grand Challenge. Proceedings of the Computer Vision and Pattern Recognition, San Diego, CA, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/7\/2080\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:10:38Z","timestamp":1760195438000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/7\/2080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,28]]},"references-count":58,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2018,7]]}},"alternative-id":["s18072080"],"URL":"https:\/\/doi.org\/10.3390\/s18072080","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,28]]}}}