Face detection can be termed as a one of the component of object-class detection. Detecting an object's location and size from an image or a video is known as object-class detection. So, in the face detection methods, we basically try to find the location of the facial region of a human. There are many algorithms available for the face detection. Some are slow, while some are robust. But not every face detection algorithm can be implemented on the hardware. Here we will implement the method involving RCT Colour based segmentation. In this paper, we propose an algorithm to detect faces from an image considering HSV, YCbCr and RGB colour spaces. We will also put some masking so as to remove unwanted detected portions. © 2016 IEEE.