Surveillance system using IP camera and face-detection algorithm

This paper presents an efficient video surveillance system which consists of a network camera and an algorithm for automatically detection of the human faces in the monitoring area via real time video contents analysis. The main contribution of this research consists in a software application which is able to process the images received from the camera in order to detect human faces and trigger the process of saving the live stream as a video file. The algorithm for face-detection is based on the integral image (summed area table) - a model which allows the calculation of the sum of all pixels values from any rectangular area in the original image by doing only four operations of addition or subtraction. In addition, the application also includes a file containing data about needed tests in the detection algorithm by analyzing multiple images as templates. The application is written in C# language and experimental results are presented for images with different sizes and backgrounds.