Video surveillance applications present a problem for the designer of computer vision algorithms. In most cases lighting condition is poor due to the environment and the distance of cameras affect the accuracy of detection. In this paper we develop first an algorithm that detects faces from a video file with a poor illumination, and then an efficient tracker is used to follow the continuity of the faces. Some image pre-processing algorithms are applied like (histogram equalization and manual-dynamic thresholding) to reduce the false faces rate. Hybrid face detector is applied (for both frontal and pose orientation faces) using haar-cascades frontal face and profile face classifiers. The proposed system will be tested on a complex video environment (fast objects in movement) to evaluate the performance in terms of accuracy detection and the efficiency. Test results show that the detection rate accuracy of the faces in the video with the complex environment is very high and reach about 99.05%.

Face Detector; Face Tracker; Frontal Classifier; Profile Classifier; Complex Video Enviroment

[1] J. Suneetha, “A Survey on Video-based Face Recognition Approaches”, International Journal of Application or Innovation in Engineering & Management, Volume-3, Issue-2, Page No (208-215), 2014.
[2] A. M. Aree, Astrid Laubenheimer and A. S. Yusra, “Efficient Face Tracking and Detection in Video: Based on Template Matching”, in the Proceeding of the International Conference on Image Processing, Computer Vision, and Pattern Recognition IPCV, Nevada, USA, Page No (584-591), 2012.
[3] C. Kublbeck and A. Ernst, “Face detection and tracking in video sequences using the modified census transformation”, Image and Vision Computing, Elsevier, Volume-24, Issue-6, Page No (564-572), 2006.
[4] S.V. Viraktamath et al, “Face Detection and Tracking using OpenCV”, The SIJ Transactions on Computer Networks & Communication Engineering, Volume-1, Issue-2, Page No (45-50), 2013.
[5] P. S. Hiremath, M. Hiremath and R. Mahesh, “Face Detection and Tracking in Video Sequence using Fuzzy Geometric Face Model and Mean Shift,” International Journal of Advanced Trends in Computer Science and Engineering, Volume-2, Issue-1, Page No (41-46), 2013.
[6] B. Moghaddam and A. Pentland, “Probabilistic Visual Learning for Object Representation”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Volume-19, Issue-7, Page No (696-710), 1997.
[7] H. A. Rowley, S. Baluja, and T. Kanade, "Neural Network-Based Face Detection", IEEE Transaction on Pattern Analysis and Machine Intelligence, Volume-20, Issue-1, Page No (23-38), 1998.
[8] P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features", In Proceedings of International Conference on Computer Vision and Pattern Recognition, Volume-1, Page No (511-518), 2001.
[9] R. L. Hsu, M. Abdel-Mottaleb and A. K. Jain, "Face Detection in Color Images", IEEE Transaction on Pattern Analysis and Machine Intelligence, Volume-24, Issue-5, Page No (696-706), 2002.
[10] H. Wang, Y. Wang, And Y. Cao ,"Video-based Face Recognition: A Survey", International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2009, Volume-3, Issue-2, Page No (2809-2818).