Face Detection at the Low Light Environments

Today, with the advancement of technology, the use of tools for extracting information from video are much wider in terms of both visual power and the processing power. High-speed car, perfect detection accuracy, business diversity in the fields of medical, home appliances, smart cars, humanoid robots, military systems and the commercialization makes these systems cost effective. Among the most widely used image processing tools are detection systems and investigate the faces of people. Change the brightness is one of the challenges in face recognition under complex lighting conditions. There are multiple various methods for removing lighting changes. In this study, it is used of the methods, the non-local means, non-local adaptive means; Retinex single comparative scale and the PCA method input data was provided by using calculated Eigen-face and finally, the face Detection was conducted using the PCA. It should be noted that the used image bases include Extended Yale B and CMU PIE database, which contains a variety of images along with the different lighting intensities and angles. The obtained results show the proposed method that the maximum recognition achieved in a space of 360 dimensional PCA is about 97.5 percent, and detection speed is equal to 2.55 milliseconds that is very impressive compared to the high volume of used database.