Face detection is very important nowadays because of increasing demand of security in society. It has become inseparable part of machine vision, biometric researches, pattern recognition and video surveillance. In this paper, we propose to detect face from image with varying lighting condition and complex background. This method relies on a two step process. First, we detect human skin regions. The detection of facial features from image is on the basis of pixel measurement. This is done by the conversion of RGB image into the YCbCr color space using proposed algorithm in order to observe the human face regions. This operation needs for the change of color image into gray scale image and also the removal of non face object. Then we construct eye and mouth maps in order to work on the triangle relationship between them. The result works well on wide range of facial variation in color, position, scale and orientation with photo collection including both indoors and outdoors.