Yiwen Chen
ABSTRACT
At present, it has become normal for people to travel with masks. In order to meet the challenge of face recognition caused by mask occlusion, a new method for landmark localization of masked face was proposed in this study. Correspondingly, a 68-point shape model including face and mask was designed and the distribution of the related landmarks was pre-positioned according to the fitting characteristics between the face and mask. To generate a regressor with function of accurate localization of facial landmarks, the masked face dataset marked by the shape model was constructed; Meanwhile, the regression tree integration algorithm was used to accurately locate the pre-positioned landmarks of the masked face. By means of the method established in this study, the tested value of IPN and ION is respectively equal to 5.68 and 3.65, being less than those of other classical algorithms. The experimental results indicate that this method can achieve an acceptable landmark localization effect and is likely to provide certain technical supports for the masked face recognition.
- XIN J, TAN X.Face alignment in-the-wild: A survey[J].Computer Vision Image Understanding, 2017, 162: 1-22.Google Scholar
- CHRYSOS G G, ANTONAKOS E, SNAPE P, A comprehensive performance evaluation of deformable face tracking ”in-the-wild”[J].International Journal of Computer Vision, 2016, 126 (2): 198-232.Google Scholar
- KHAN R A, MEYER A, KONIK H, Saliency based framework for facial expression recognition[J].Frontiers of Computer Science (electronic), 2019, (1): 183-198.Google Scholar
- CHI N D, LUU K, QUACH K G, Deep appearance models: A deep boltzmann machine approach for face modeling[J].International Journal of Computer Vision, 2019, 127(3): 437-455.Google Scholar
- Liu J, Cheng P, Wu B, Yang Z. Face characterization and 3D reconstruction based on self-supervised deep learning [J].Sensors and Microsystems, 2019,38 (9): 126-128,133.Google Scholar
- COOTES T.Active shape models-their training and application[J].Comput.Vis.Image Understand, 1995, 61(1): 38-59.Google ScholarDigital Library
- WANG J, YUAN Y, YU G.Face attention network: An effective face detector for the occluded faces[J].2020, https://blog.csdn.net/cdknight happy/article/details/105773331.Google Scholar
- CHEN Y, SONG L, RAN H.Masquer hunter: Adversarial occlusion-aware face detection : 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)[C].Los Angeles: 2018 IEEE, 2018.Google Scholar
- Zou Baihan, Qin Yating, Yuan Xiaobing, Status study of mask face detection methods based on lightweight CNN [J].Software, 2020,41 (8): 186-188.Google Scholar
- Chen Jiali, Liu Kechun, Tang cong, A method to identify the key points of the face and forehead: China, CN201811493855.7 [P].2019-02-22.Google Scholar
- Li Yuan, Yang Yandan, Wang Jinwei.Identification of the eye key points and the training method and device of the detection model: China, 201910541988.5 [P].2020-04-03.Google Scholar
- KAZEMI V, SULLIVAN J.One millisecond face alignment with an ensemble of regression trees : 2014 IEEE Conference on Computer Vision Pattern Recognition [C]Columbus: 2014 IEEE, 2014..Google Scholar
- CABANI A, HAMMOUDI K, BENHABILES H, Maskedface-net a dataset of correctly/incorrectly masked face images in the context of covid-19[J].Smart Health(Amsterdam, Netherlands), 2020, 19: 100144.Google Scholar
- SAGONAS C, TZIMIROPOULOS G, ZAFEIRIOU S, 300 faces in-the-wild challenge: The first facial landmark localization challenge : Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops [C].Sydney: 2013 IEEE, 2013.Google Scholar
- GUO X, LI S, ZHANG J, Pfld: A practical facial landmark detector[J].Computer Vision and Pattern Recognition, 2019(lasted revised 3 Mar 2019).Google Scholar
- Wu W , Qian C , Yang S , Look at Boundary: A Boundary-Aware Face Alignment Algorithm : 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition [C].Salt Lake City: 2018 IEEE, 2018.Google Scholar
Recommendations
Automatic face analysis system based on face recognition and facial physiognomy
ICHIT'06: Proceedings of the 1st international conference on Advances in hybrid information technologyAn automatic face analysis system is proposed which uses face recognition and facial physiognomy. It first detects human's face, extracts its features, and classifies the shape of facial features. It will analyze the person's facial physiognomy and then ...
Face Mask Invariant End-to-End Face Recognition
Computer Vision – ECCV 2020 WorkshopsAbstractThis paper introduces an end-to-end face recognition network that is invariant to face images with face masks. Conventional face recognition networks have degraded performance on images with face masks due to inaccurate landmark prediction and ...
Face Recognition Through Different Facial Expressions
Face recognition has become an accessible issue for experts as well as ordinary people as it is a focal non-interfering biometric modality. In this paper, we introduced a new approach to perform face recognition under varying facial expressions. The ...
Comments