Adaptive facial expression recognition method based on MBP and HMOG feature

Because of the limitation of Monogenic waves´ extraction from expression texture, this thesis proposes an adaptive facial expression feature fusion method based on MBP (monogenic binary pattern) and Histogram of HMOG (monogenic orientated gradients). To begin with our method, we get information of orientation, phase and magnitude component from filtered image by monogenic waves, besides, extract and fuse texture information from orientation and magnitude component to recognize facial expression. However single texture feature have some inadequacies for facial expression recognition. First of all, this paper describes a new kind of HMOG feature inspired by thoughts of HOG (histogram of oriented gradients) to indicate shape information of facial image. Secondly, acquiring best adaptive weights of expression block through information entropy. Finally, we classify the expression image using Nearest Neighbor to get the final result of effect of proposed method. In order to verify the efficiency of the methods above, we do a large number of experiments and it turns out our methods have great ability to explain expression feature.