Abstract
Recent state-of-the-art Face Detection algorithms in the field of Computer Vision focus greatly on real-time processing and results. The applications using these algorithms deal with low quality video feeds having less Pixels Per Inch (ppi) and/or low frame rate. The algorithms perform well with such video feeds, but their performance deteriorates towards high quality, high data-per-frame videos. Such video files mostly exist in offline mode, that could be used for post processing by the Computer Vision applications. This paper focuses on developing such an algorithm that gives faster results on high quality videos, at par with the algorithms working on live low quality video feeds. The proposed algorithm uses Convolutional-MTCNN as base algorithm, and speeds it up for high definition videos. This paper also presents a novel solution to the problem of occlusion and detecting partial or fully hidden faces in the videos. This is achieved by using probabilistic approaches, given that the face has been identified in first few frames, to give the algorithm an estimate of where the face should be in the occluded region.
Similar content being viewed by others
References
Cao X, Wei Y, Wen F, Sun J (2012) Face alignment by explicit shape regression. In: IEEE conference on computer vision and pattern recognition, pp 2887–2894
Chrysos G G, Antonakos E, Zafeiriou S, Snape P (2015) Offline deformable face tracking in arbitrary videos. In: IEEE international conference on computer vision workshop (ICCVW), pp 954–962
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Computer society conference on computer vision and pattern recognition (CVPR’05), vol 1, pp 886–893
Ismail N, Sabri MIM (2009) Review of existing algorithms for face detection and recognition. In: World scientific and engineering academy and society (WSEAS), pp 30–39
Jia Y-B (2017) Polynomial interpolation. National Taiwan Ocean University Pub Scientific Computing
Li J, Song L, Liu C (2018) The cubic trigonometric automatic interpolation spline. IEEE/CAA J Autom Sin 5(6):1136–1141
Luo J, Liu J, Lin J, Wang Z (2020) A lightweight face detector by integrating the convolutional neural network with the image pyramid. Pattern Recogn Lett 133:180–187. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0167865520300805
Meijering E (2002) A chronology of interpolation: from ancient astronomy to modern signal and image processing. Proc IEEE 90(3):319–342
Nguyen D T, Nguyen T N, Kim H, Lee H (2019) A high-throughput and power-efficient fpga implementation of yolo cnn for object detection. IEEE Trans Very Large Scale Integr (VLSI) Syst 27(8):1861–1873
Pairo W, Loncomilla P, Ruiz-del Solar J (2019) A delay-free and robust object tracking approach for robotics applications. J Intell Robot Syst 95:07
Raja R, Sinha D T, Dubey R (2015) Recognition of human-face from side-view using progressive switching pattern and soft-computing technique. Adv Model Anal B 58:14–34, 01
Raja R, Sinha T S, Patra R K, Tiwari S (2018) Physiological trait-based biometrical authentication of human-face using lgxp and ann techniques. Int J Inf Comput Secur 10(2–3):303–320. [Online]. Available: https://www.inderscienceonline.com/doi/abs/10.1504/IJICS.2018.091468
Ranftl A, Alonso-Fernandez F, Karlsson S, Bigun J (2017) A real-time adaboost cascade face tracker based on likelihood map and optical flow. IET Biom 6:05
Ranjan R, Patel V M, Chellappa R (2019) Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans Pattern Anal Mach Intell 41(1):121–135
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR). [Online]. Available: https://doi.org/10.1109/CVPR.2015.7298682
Shen J, Zafeiriou S, Chrysos G G, Kossaifi J, Tzimiropoulos G, Pantic M (2015) The first facial landmark tracking in-the-wild challenge: Benchmark and results. In: IEEE international conference on computer vision workshop (ICCVW), pp 1003–1011
Singh S, Singh D, Yadav V (2020) Face recognition using hog feature extraction and svm classifier. 8:6437–6440, 09
Tomasi C, Kanade T (1991) Detection and tracking of point features. Int J Comput Vis
Tzimiropoulos G (2015) Project-out cascaded regression with an application to face alignment. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3659–3667
Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57:137–154, 05
Yang M -H, Kriegman D J, Ahuja N (2002) Detecting faces in images: a survey. IEEE Trans Pattern Anal Mac Intell 24(1):34–58
Yang B, Yan J, Lei Z, Li S Z (2014) Aggregate channel features for multi-view face detection. In: IEEE International joint conference on biometrics, pp 1–8
Yu B, Tao D (2019) Anchor cascade for efficient face detection. IEEE Trans Image Process 28(5):2490–2501
Zeng D, Zhao F, Ge S, Shen W (2019) Fast cascade face detection with pyramid network. Pattern Recogn Lett 119:180–186. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0167865518302125
Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499–1503
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
Akshay Mool, J. Panda and Kapil Sharma declare that they have no conflict of interest.
Additional information
Competing interest
The authors declare that they do not have any competing financial interests nor any personal relationships that could seem to have influenced the work presented by this paper.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mool, A., Panda, J. & Sharma, K. Optimizable face detection and tracking model with occlusion resolution for high quality videos. Multimed Tools Appl 81, 10391–10406 (2022). https://doi.org/10.1007/s11042-022-11958-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-11958-5