Feature Fusion Based Audio-Visual Speaker Identification Using Hidden Markov Model under Different Lighting Variations

<table>Facial image before processing for the proposed systems: (a) original image, (b) output taken from Stams Active Appearance Model, (c) extracted facial edges, (d) shape based features, (e) region of interest (ROI) selection with background noise, and (f) appearance based facial features.</table>

Applied Computational Intelligence and Soft Computing

fig2

Figure 2

Figure 2: Feature Fusion Based Audio-Visual Speaker Identification Using Hidden Markov Model under Different Lighting Variations 