Author : Varshitha Gowda H S 1
Date of Publication :7th May 2016
Abstract: Human face detection has a wide application in biometric and security fields. It finds its application in photography, video surveillance and in many other areas. This paper proposes a face detection approach using Viola Jones algorithm with a Haar features converted to integral image to decrease the computational complexity. AdaBoost algorithm is used for feature selection and attentional cascade for fast rejection of non-face windows. This approach performs fifteen times faster than other face detection algorithms. This method is implemented in college for automatic class attendance system, which takes real time image as input and detects faces crops the face region and display along with their count, which helps in taking automatic attendance. With a high accuracy, the detected faces along with the count are updated. An improved result for face detection and accuracy is obtained using this algorithm.
Reference :
-
[1] Paul Viola, Michael J. Jones, Robust Real-Time Face Detection, International Journal of Cumputer Vision 57(2), 2004.
[2] Paul Viola, Michael J. Jones, Fast Multi-view Face Detection, Mitsubishi Electric Research Laboratories, TR2003-096, August 2003.
[3] Henry A. Rowley, Shumeet Baluja, Takeo Kanade, Neural Network-Based Face Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 20, Issue 1, Jan 1998. Digital Object Identifier 10.1109/34.655647.
[4] Henry Schneiderman, Takeo Kanade, A Statistical Method for 3D Object Detection Applied To Faces and Cars, IEEE Conference on Computer Vision and Pattern Recognition 2000 proceedings, Volume 1. Digital Object Identifier 10.1109/CVPR.2000.855895
[5] Christopher M. Bishop, Pattern Recognition and Machine Learning, first edition, Springer 2006Y.
[6] P. J. Phillips, H. Moon, The Facial Recognition Technology (FERET) Database. http://www.itl.nist.gov/iad/humanid/feret/feret_master. html