Abstract
Beard and hair detection and segmentation have a significant role in gender identification, age assessment, and facial recognition. Due to the variability of their forms, colors, and intensities and the impact of shadows and light objects. This paper has proposed an efficient state-of-the-art system for beard and hair detection and segmentation for changing color in challenging facial images. After segmentation, the color of hair and beard can be changed. We have used a modified version of a Mask R-CNN model for hair and beard detection and segmentation. We have collected and prepared a dataset of 1500 images equally divided into both hair and beard images. This dataset is online available on the NCAI1 website. Finally, we have retrained a modified version of Mask R-CNN through transfer learning on our dataset to detect and segment out hair and beard on any given image. Mask R-CNN has outperformed compared to earlier systems designed for the same task with an accuracy of 91.2%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
https://apps.apple.com/us/app/faceapp-ai-face-editor/id1180884341 access at: Aug 17, 2021
Meethongjan K, Dzulkifli M, Rehman A, Altameem A, Saba T (2013) An intelligent fused approach for face recognition. J Intell Syst 22(2):197–212
Sharif M, Naz F, Yasmin M, Shahid MA, Rehman A (2017) Face recognition: a survey. J Eng Sci Technol Rev 10(2):166–177
Saba T, Kashif M, Afzal E (2021) “Facial expression recognition using patch-based lbps in an unconstrained environment”, Proc. IEEE first international conference on artificial intelligence and data analytics (CAIDA), pp 105–108
Yacoob Y, Davis LS (2006) Detection and analysis of hair. IEEE Trans Pattern Anal Mach Intell 28(7):1164–1169. https://doi.org/10.1109/TPAMI.2006.139
Raza M, Sharif M, Yasmin M, Khan MA, Saba T, Fernandes SL (2018) Appearance based pedestrians’ gender recognition by employing stacked auto encoders in deep learning. Futur Gener Comput Syst 88:28–39
Khan MZ, Jabeen S, Khan MU, Saba T, Rehmat A, Rehman A, Tariq U (2020) A realistic image generation of face from text description using the fully trained generative adversarial networks. IEEE Access 10(9):1250–1260
Yavuzkilic S, Sengur A, Akhtar Z, Siddique K (2021) Spotting deepfakes and face manipulations by fusing features from multi-stream cnns models. Symmetry 13(8):1352
Rowley HA, Baluja S, Kanade T (Jan 1998) “Neural network-based face detection”, IEEE Trans Pattern Anal Mach Intell 20(1):23–38
Chen D, Ren S, Wei Y, Cao X, Sun J (2014) “Joint cascade face detection and alignment”. Proc Eur Conf Comput Vis, pp 109–122
Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154
Li J, Zhang Y (2013) “Learning surf cascade for fast and accurate object detection”. Proc IEEE Conf Comput Vis Pattern Recog, pp 3468–3475
Le THN, Luu K, Seshadri K, Savvides M (2012) “Beard and moustache segmentation using sparse classifiers on self-quotient images,” in Proceedings—international conference on image processing, ICIP, pp 165–168. https://doi.org/10.1109/ICIP.2012.6466821
Yoon H-S, Park S-W, Yoo J-H (2021) Real-time hair segmentation using mobile-unet. Electronics 10(2):99
Nguyen MH, Lalonde JF, Efros AA, De La Torre F (2008) Image—based shaving. Comput Graph Forum 27(2):627–635. https://doi.org/10.1111/j.1467-8659.2008.01160.x
Le THN, Luu K, Zhu C, Savvides M (2017) Semi self- training beard/moustache detection and segmentation simultaneously. Image Vis Comput 58:214–223. https://doi.org/10.1016/j.imavis.2016.07.009
Shen Y, Peng Z, Zhang Y (2014) “Image based hair segmentation algorithm for the application of automatic facial caricature synthesis.” Sci World J 2014. https://doi.org/10.1155/2014/748634
Acknowledgements
We want to offer our sincere thanks to the National Center of Artificial Intelligence for ultimately supporting our exploration work. The authors also want to acknowledge the appreciation of all group members (associates & the executives) and association (KICS) for their help, commitment, specialized meetings, and information sharing exertion for this. Without their support and encouragement, this research work could not be accomplished.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ubaid, M.T., Khalil, M., Khan, M.U.G., Saba, T., Rehman, A. (2022). Beard and Hair Detection, Segmentation and Changing Color Using Mask R-CNN. In: Ullah, A., Anwar, S., Rocha, Á., Gill, S. (eds) Proceedings of International Conference on Information Technology and Applications. Lecture Notes in Networks and Systems, vol 350. Springer, Singapore. https://doi.org/10.1007/978-981-16-7618-5_6
Download citation
DOI: https://doi.org/10.1007/978-981-16-7618-5_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7617-8
Online ISBN: 978-981-16-7618-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)