Face Recognition using DWT with HMM

Abstract

This paper presents an efficient face recognition system based on Hidden MarkovModel (HMM) and the simplest type “Haar” of the Discrete Wavelet Transform(DWT). The one dimensional ergodic HMM with Gaussian outputs, which representthe simplest and robust type of HMM, is used in the proposed work. A novel methodis introduced for selecting the training images implemented by choosing the imagesthat have the odd identifying numbers from the database. Some of these images arereplaced according to the trial-and-error results. The proposed work achieves themaximum recognition rate (100%), where the experiments are carried out on the ORLface database.