The development of feature improvement for illumination face image classification using hybird algorithm

Abstract

Image normalization is the important process for improving the quality for illumination image consisted of shadow and light that is affected with the performance of the feature extraction and face recognition. This research proposed the development of Image normalization for illumination such as dark light and over light that creates some visible face area and it is unable to use the normal face recognition process. This research proposed the main algorithm called self-quotient image hybrid with the weber, mean filter and wavelet. The standard dataset called Yale B database is used for demonstrating the performance of our proposed algorithm. The data is divided into 4 set. The self-quotient image together with weber face and mean filter creates the best result for reducing the illumination from shadow and light at 99.4%