Abstract
Compared with traditional face detection methods, deep learning methods can better deal with face detection in unconstrained environment. In this paper, based on the original Multi-Task Cascaded Convolutional Networks (MTCNN), we make corresponding improvements on it. On the premise of ensuring that the accuracy of the improved algorithm for face detection is similar to the original, we improve the detection speed. First of all, the original network structure is optimized. In order to improve the detection speed, the amount of computation should be reduced as much as possible. Therefore, it is proposed to use Depthwise convolution in MobileNet instead of conventional convolution; in addition, median filter is used before image detection to reduce some noise and improve the performance of the algorithm. After training on the Wider Face and Celeba data set, the test images were tested. Experimental results show that the performance of the improved MTCNN is not significantly reduced, and the detection speed is significantly improved.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, T., Luo, H., Jia, W., Liu, A., Xie, M.: MTES: an intelligent trust evaluation scheme in sensor-cloud-enabled industrial internet of things. IEEE Trans. Ind. Inf. 16(3), 2054–2062 (2020)
Huang, M.F., Liu, A.F., Wang, T., Huang, C.Q.: Green data gathering under delay differentiated services constraint for internet of things. Wirel. Commun. Mobile Comput. 2018(3), 1–23 (2018)
Tang, J., Liu, A., Wang, T.: An aggregate signature based trust routing for data gathering in sensor networks. Secur. Commun. Netw. (S&CN) 2018, 1–30 (2018)
Henry, A.R., Baluja, S., Anade, T.K.: Neural network-based face detection. IEEE Trans. Pattern Anal. Mach. Intell. 20(1), 23–38 (1998)
Henry, A. R., Baluja, S., Anade, T. K.: Rotation Invariant Neural Network-Based Face Detection. In: Proceediongs of Computer Vision and Pattern Recognition (CVPR), pp. 38–44 (1998)
Li, S.Z., Zhu, L., Zhang, Z., Blake, A., Zhang, H., Shum, H.: Statistical learning of multi-view face detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 67–81. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-47979-1_5
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2018)
Li, H., Lin, Z., Shen, X., Brandt, J., Hua, G.: A convolutional neural network cascade for face detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp. 5325–5334 (2015)
Jain, V., Learned-Miller, E.: FDDB: a benchmark for facedetection in unconstrained settings. University of Massachusetts(Relatório Técnico UM-CS-2010–009), Amherst, pp. 329–337 (2010)
Ranjan, R., Patel, V.M., Chellappa, R.: A deep pyramid deformable part model for face detection. In: IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS), Arlington, pp. 1–8 (2015)
Yang, S., Luo, P., Loy, C.C., Tang, X.: Faceness-Net: face detection through deep facial part responses. IEEE Trans. Pattern Anal. Mach. Intell. 40(8), 1845–1859 (2018)
Chen, D., Ren, S., Wei, Y., Cao, X., Sun, J.: Joint cascade face detection and alignment. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 109–122. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_8
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jiang, X., Xiang, Y. (2021). Face Detection Using Improved Multi-task Cascaded Convolutional Networks. In: Wang, G., Chen, B., Li, W., Di Pietro, R., Yan, X., Han, H. (eds) Security, Privacy, and Anonymity in Computation, Communication, and Storage. SpaCCS 2020. Lecture Notes in Computer Science(), vol 12383. Springer, Cham. https://doi.org/10.1007/978-3-030-68884-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-68884-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68883-7
Online ISBN: 978-3-030-68884-4
eBook Packages: Computer ScienceComputer Science (R0)