Frontal human face detection using skin detection,face matching and haarcascade
Boshra Alsheikh Wais 1, Hasan Erbay 2*
1Kirikkale University , Kirikkale , Turkey
2Kirikkale University , Kirikkale , Turkey
* Corresponding author: hxe68@yahoo.com
Presented at the 3rd International Symposium on Innovative Approaches in Scientific Studies (Engineering and Natural Sciences) (ISAS2019-ENS), Ankara, Turkey, Apr 19, 2019
SETSCI Conference Proceedings, 2019, 4, Page (s): 232-237
Published Date: 01 June 2019
Human face detection one of the most important fields that attract searches since a long time ago until now because of the huge number of applications that benefit from face detection and recognition like crowd surveillance, Attendance System, ATM and other. In this paper we propose a method of frontal face detection that consists in general from two steps human skin detection and human face matching. For human skin detection we suppose ranges for skin color in two color spaces YCbCr and HSV because RGB model affect to the changes of luminance and in this space we cannot separate it from the color information .For getting almost clear image and getting right information from the image we apply blurring techniques (Median and Bilateral) and morphological transformations to delete the noises (Dilation, Erosion, Opening..). After we get the skin region we find the contours after converting the image to black and white .The contour region that contains at least two contours inside it (two eyes) presents the region that contains absolutely the face. After that we apply face matching using template of frontal human face .At last we compare the model with haarcascade classifier and combine the skin detection and haarcascade and get the results.
Keywords - Face detection, skin color detection, color spaces, human face matching, haarcascade, contours
[1] Face Detection Based On A Model Of The Skin Color With Constraints And Template Matching By S. Kherchaoui and A. Houacine LCPTS, Faculty of Electronics & Informatics USTHB, BP32 El Alia, Bab Ezzouar, Algiers, Algeria., 978-1-4244-8611- 3/10/$26.00 ©2010 IEEE.
[2] A Robust Face Detection Method Based on Skin Color and Edges , Deepak Ghimire and Joonwhoan Lee, e National Research Foundation of Korea grant.
[3] An Innovative Face Detection based on Skin Color Segmentation, Kamarul Hawari Bin Ghazali, Jie Ma, Rui Xiao, International Journal of Computer Applications (0975 – 8887) Volume 34– No.2, November 201.
[4] A novel approach for face detection using hybrid skin color model Shalini Yadav ,Neeta Nain, Springer International Publishing Switzerland 2016.
[5] Human Skin Detection Using RGB, HSV and YCbCr Color Models, S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, and J. Jatakia
[6] Face Detection Based On A Model Of The Skin Color With Constraints And Template Matching, S. Kherchaoui and A. Houacine , Faculty of Electronics & Informatics Algeria, 2010 IEEE.
[7] Human face detection algorithm via Haar cascade classifier combined with three additional classifiers, Li Cuimei1, Qi Zhiliang, Jia Nan, Wu Jianhua, School of Communication and Electronics, Jiangxi Science & Technology Normal University Nanchang, China, 2017 IEEE 13th International Conference on Electronic Measurement & Instruments.
[8] Face Recognition Using Contour Matching, S. T. Gandhe, K. T. Talele, and A.G.Keskar, IAENG International Journal of Computer Science, 20 May 2008.
[9] Enhancement of YCbCr Algorithm for Skin Color Segmentation, Sumandeep Kaur, Kuldeep Singh, Computer Science Department, Guru Kashi University, Talwandi Sabo, India1, International Journal of Advanced Research in Computer and Communication Engineering, June 2016.
[10] Noise removal and enhancement of binary images using morphological operations, Nursuriati Jamil, Tengku Sembok, Zainab Abu Bakar, Information Technology, 2008. ITSim 2008. International Symposium on Volume 14.
|
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
