Facial Keypoint Detection Using Deep Learning and Computer Vision
With the advent of Computer Vision, research scientists across the world are working constantly working to expedite the advancement of Facial Landmarking system. It is a paramount step for various Facial processing operations. The applications range from facial recognition to Emotion recognition. These days, we have systems that identify people in images and tag them accordingly. There are mobile applications which identify the emotion of a person in an image and return the appropriate emoticon. The systems are put to use for applications ranging from personal security to national security. In this work, we have agglomerated computer vision techniques and Deep Learning algorithms to develop an end-to-end facial keypoint recognition system. Facial keypoints are discrete points around eyes, nose, mouth on any face. The implementation begins from Investigating OpenCV, pre-processing of images and Detection of faces. Further, a convolutional Neural network is trained for detecting eyes, nose and mouth. Finally, the CV pipeline is completed by the two parts mentioned above.
KeywordsPipeline Edges De-noising Blurring Detection Losses Landmark Recognition Robust
We would like to thank Dr. Suresh D, Department of Electronics and Communication, RNS Institute of Technology for his technical and writing assistance.
- 1.Valstar, M., Martinez, B., Binefa, X., Pantic, M.: Facial point detection using boosted regression and graph models. In: Proceedings of Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp. 2729–2736 (2010)Google Scholar
- 4.Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. In: Proceedings of Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, pp. 545–552 (2011)Google Scholar
- 5.Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 397–403 (2013)Google Scholar
- 6.Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Incremental face alignment in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1859–1866 (2014)Google Scholar
- 7.Wu, Y., Ji, Q.: Facial landmark detection: a literature survey. Int. J. Comput. Vis. Received Nov 2016. Accepted Apr 2018Google Scholar
- 9.Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: Proceedings of the International Conference on Pattern Recognition, pp. 586–591 (1991)Google Scholar
- 10.Negi, R.S., Garg, R.: Face recognition using hausdroff distance as a matching algorithm. Int. J. Sci. Res. 4(9) (2016)Google Scholar
- 11.Dewan, M.A.A., Qiao, D., Lin, F., Wen, D.: An approach to improving single sample face recognition using high confident tracking trajectories. In: Canadian Conference on Artificial Intelligence, pp. 115–121. Springer, Cham (2016)Google Scholar
- 12.Shi, X., Wu, J., Ling, X., Zheng, Q., Pan, X., Zhao, Z.: Real-time face recognition method based on the threshold determination of the positive face sequence. In: Proceedings of the 22nd International Conference on Industrial Engineering and Engineering Management 2015, pp. 125–136. Atlantis Press (2016)Google Scholar
- 13.Goswami, G., Vatsa, M., Singh, R.: Face recognition with RGB-D images using kinect. In: Face Recognition Across the Imaging Spectrum, pp. 281–303. Springer, Cham (2016)Google Scholar
- 14.Dahal, B., Alsadoon, A., Prasad, P.W.C., Elchouemi, A.: Incorporating skin color for improved face detection and tracking system. In: 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), pp. 173–176. IEEE (2016)Google Scholar