Automated Facial Wrinkles Annotator
This paper presents an automated facial wrinkles annotator for coarse wrinkles, fine wrinkles and wrinkle depth map extraction. First we extended Hybrid Hessian Filter by introducing a multi-scale filter to isolate the coarse wrinkles from fine wrinkles. Then we generate a wrinkle probabilistic map. When evaluated on 20 high resolution full face images (10 from our in-house dataset and 10 from FERET dataset), we achieved good accuracy when the result of coarse wrinkles was validated with manual annotation. Furthermore, we visually illustrate the ability of the annotator in detecting fine wrinkles. This paper advances the field by automate the localisation of the fine wrinkles, which might not be possible to annotate manually. Our automated facial wrinkles annotator will be beneficial to large-scale data annotation and cosmetic applications.
KeywordsWrinkles annotator Hessian filter Wrinkles depth
This work was supported by the Royal Society Industry Fellowship (IF160006). The authors would like to thanks Phillips et al.  for the FERET dataset.
- 1.Alarifi, J.S., Goyal, M., Davison, A.K., Dancey, D., Khan, R., Yap, M.H.: Facial skin classification using convolutional neural networks. In: Karray, F., Campilho, A., Cheriet, F. (eds.) ICIAR 2017. LNCS, vol. 10317, pp. 479–485. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59876-5_53CrossRefGoogle Scholar
- 3.Batool, N., Chellappa, R.: A Markov point process model for wrinkles in human faces. In: 2012 19th IEEE International Conference on Image Processing, pp. 1809–1812. IEEE (2012)Google Scholar
- 7.Ng, C.C., Yap, M.H., Cheng, Y.T., Hsu, G.S.: Hybrid ageing patterns for face age estimation. Image Vis. Comput. 69, 92–102 (2018). https://doi.org/10.1016/j.imavis.2017.08.005, http://www.sciencedirect.com/science/article/pii/S026288561730121XCrossRefGoogle Scholar
- 10.Osman, O.F., Elbashir, R.M.I., Abbass, I.E., Kendrick, C., Goyal, M., Yap, M.H.: Automated assessment of facial wrinkling: a case study on the effect of smoking. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1081–1086, October 2017. https://doi.org/10.1109/SMC.2017.8122755