Illumination invariant face recognition via multiscale filter faces and voting technique

In this paper, we propose a novel technique for face recognition under varying illumination. Our technique extracts twelve filter faces (FF) and computes their HOG features, and then finds the class label of the unknown face image according to each generated feature map. We perform majority voting from the found twelve class labels to determine the final class label of the input face image. By examining the structure of the FF’s defined in this paper, we can see that our FF’s can extract directional features from the input face images and they can supress random noise as well. This is the main reason why our new method performs so well for illumination invariant face recognition. Experimental results demonstrate that our new method achieves the highest correct recognition rate 99.3% (100%) for the Extended Yale Face B (CMU Pose, Illumination and Expression Face) dataset.