Abstract
In recent years, face detection and face recognition were widely used in fields like identity-verification system, security system and financial system. However, some of the real-time face detection tasks are still challenging due to the overflowed computational cost of a discriminative system. To resolve this issue, we propose a cascaded network based on CNN, which has simple architecture and light-weighted parameters. The network consists of three stages and operates with a image pyramid (same image with different resolutions), the first stage quickly discriminates faces (proposals) from background, and the other two stage specifically evaluate those proposals to determinate whether a proposal contains face or not. We also address an adaptive method that dynamically drops those redundant proposal regions generated in first stage to avoid prohibitive computation. The model we trained runs at 180 ms for processing a single image on CPU, and keeps an accuracy around 98.4%.
This work was supported by 2019 Industrial Internet Innovation Development Project-Industrial Internet Network Security Public Service Platform Project (TC190H3WN).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Y.M.: Research on Face Detection Matching and Recognition Algorithm. Harbin Institute of Technology, Harbin (2018). (in Chinese)
Wang, C.J.: Research on Face Detection Method Based on Fully Convolutional Neural Network. Xiamen University, Xiamen (2018). (in Chinese)
Bian, H.: Research on Face Detection and Recognition Algorithm. Beijing University Of Technology, Beijing (2017). (in Chinese)
Kalinovskii, I., Spitsyn, V.: Compact convolutional neural network cascade for face detection. Comput. Sci. 2(2), 110 (2015)
Mathias, M., Benenson, R., Pedersoli, M., Van Gool, L.: Face detection without bells and whistles. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 720–735. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_47
Yan, J., Lei, Z., Wen, L., Li, S.: The fastest deformable part model for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2497–2504 (2014)
Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2879–2886 (2012)
Sun, X., Wu, P., Hoi, S.C.H.: Face detection using deep learning: an improved faster RCNN approach. Neurocomputing 299, 42–50 (2018)
Shi, X., Shan, S., Kan, M., et al.: Real-time rotation-invariant face detection with progressive calibration networks (2018)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137–154 (2004)
Li, J., Wang, T., Zhang, Y.: Face detection using surf cascade. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 2183–2190. IEEE (2011)
Li, H., Lin, Z., Shen, X., et al.: A convolutional neural network cascade for face detection. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2015)
Yang, Z,. Nevatia, R.: A multi-scale cascade fully convolutional network face detector (2016)
Dong, Y., Wu, Y.: Adaptive cascade deep convolutional neural networks for face alignment. Comput. Stand. Interfaces 42, 105–112 (2015)
Zhou, E., Fan, H., Cao, Z., et al.: Extensive facial landmark localization with coarse-to-fine convolutional network cascade. In: Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops. IEEE (2013)
Chen, J.C., Kumar, A., Ranjan, R., et al.: A cascaded convolutional neural network for age estimation of unconstrained faces. In: 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS). IEEE (2016)
Diba, A., Sharma, V., Pazandeh, A., et al.: Weakly supervised cascaded convolutional networks (2017)
Zhang, K., Zhang, Z., Wang, H., et al.: Detecting faces using inside cascaded contextual CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE (2017)
Ranjan, R., Patel, V.M., Chellappa, R.: HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition (2019)
Guo, G., Wang, H., Yan, Y., et al.: A fast face detection method via convolutional neural network (2018)
Yu, C., Zhu, X., Lei, Z., et al.: Out-of-distribution detection for reliable face recognition. IEEE Signal Process. Lett. PP(99), 1 (2020)
Dong, Z., et al.: Face detection in security monitoring based on artificial intelligence video retrieval technology. IEEE Access 8, 62433–63421 (2020)
Ke, X., Li, J., Guo, W.: Dense small face detection based on regional cascade multi-scale method. IET Image Proc. 13(14), 2796–2804 (2019)
Face detection with different scales based on faster R-CNN. IEEE Trans. Cybern. 1–12 (2019)
Yu, B., Tao, D.: Anchor cascade for efficient face detection. IEEE Trans. Image Process. 28(5), 2490–2501 (2019)
Han, S., et al.: Location privacy-preserving distance computation for spatial crowdsourcing. IEEE Internet Things J. 7, 1 (2020)
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
Liu, G., Lin, J., Ding, Y., Yang, S., Xu, Y. (2020). A New Face Detection Framework Based on Adaptive Cascaded Network. In: Xu, G., Liang, K., Su, C. (eds) Frontiers in Cyber Security. FCS 2020. Communications in Computer and Information Science, vol 1286. Springer, Singapore. https://doi.org/10.1007/978-981-15-9739-8_18
Download citation
DOI: https://doi.org/10.1007/978-981-15-9739-8_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9738-1
Online ISBN: 978-981-15-9739-8
eBook Packages: Computer ScienceComputer Science (R0)