In this study a framework for fast face detection is presented. The features used in the system are low order Central Geometrical Moments (CGMs) of face components and their horizontal and vertical gradients. To speed up the detection process we have utilized a fast method to compute CGMs locally in the feature extraction phase and in the classification phase we have used a fast multistage classifier. To enable each stage of the classifier to operate as fast as possible, in each stage, classification is carried out by using the optimal set of features which are selected for that particular stage according to a classification error measure. To detect faces in an image, a window the same size as the faces to be detected, scans the image and in each location the part of the image contained in the window is input to the multistage classifier which quickly discards background regions within its initial stages and spends more computation on promising face-like regions. The presented results show that the proposed system yields good performance in terms of detection and false positive rates. The proposed framework is not limited to detecting faces and shall be used to detect other objects in an image as well.