Face detection is a significant research topic to contrive identity for many automated systems. We present a novel face detection algorithm to detect a single face in an image sequence in the real-time environment by finding structural features. The proposed method allows the user to detect the face in case the lighting conditions, pose, and viewpoint vary. The proposed algorithm combines two segmentation approaches. The first approach is a Pixel-based approach by using the components Y, Cb, and Cr in YCbCr color model as threshold conditions to segment the image into luminance and chrominance components. Based on the components of YCbCr color model, the pixel can be classified to have skin tone if it's value is between two specific thresholds. The second approach is an Edgebased approach by using Roberts cross operator. It approximates the magnitude of the gradient of the test image. It also separates the integrated regions into the face and highlights these regions of high spatial gradients which correspond to the edges of the face. The new algorithm achieves high detection rate and low false positive rate.