Title: A novel method for detection and extraction of human face for video surveillance applications

Authors: Mritunjay Rai; R.K. Yadav

Addresses: Department of Electronics & Communication Engineering, JRE Group of Institutions, Greater Noida, India ' Department of Electronics & Communication Engineering, JRE Group of Institutions, Greater Noida, India

Abstract: This paper deals with the algorithm for extracting human skin region through skin detection and skin segmentation from a video. At first, the change of shot is detected and then extraction of image (if any) is done from detected shots. Once the image is detected, it gets converted into an HSV image and then skin segmentation is done. Conversion of an image into an HSV helps to work in single variable (i.e. variable being the only hue value). This algorithm will automatically provide change of shots, skin detection, skin segmentation and then extraction of the face. This entire algorithm is done under the Image Processing Toolbox (IPT) of MATLAB. Moreover, Fuzzy Logic is also used in this paper for thresholding the hue values for skin segmentation and skin detection. This paper provides a detailed idea of extracting the human face from a video automatically.

Keywords: skin segmentation; skin detection; face extraction; fuzzy logic; video surveillance; image processing; thresholding; change of shot.

DOI: 10.1504/IJSISE.2016.076226

International Journal of Signal and Imaging Systems Engineering, 2016 Vol.9 No.3, pp.165 - 173

Received: 09 Oct 2013
Accepted: 08 May 2014
Published online: 30 Apr 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article