Person-independent facial expression recognition based on local directional compact pattern

This paper proposes a novel descriptor for facial expression recognition called the Local Directional Compact Pattern (LDCP), which encodes the prominent information of local facial textures in a simple and compact way. We obtain edge responses for the local neighborhood of each pixel in four different directions by convolving the symmetric compass masks with the face image. LDCP uses direction, sign, and position information of the two top edge responses to generate a more distinctive code than existing methods that allows us to distinguish different textures with similar gradient directions. Unlike other methods in which the whole face is uniformly divided into several blocks to obtain a global feature vector by concatenating the histogram of each block, we select emotion-related blocks from the feature map to obtain the histogram-based feature vector of each block, which have a different contribution to exhibiting facial expressions. Again, we assign a weight to each block to classify facial expressions using a robust kernel representation algorithm. We conduct our experiments on the CK+, FACES, MMI, and JAFFE datasets to compare our LDCP descriptor performance with 20 existing descriptors in terms of the number of bits, base length, feature extraction time, and recognition rate. In addition, we compare our proposed method with the recent state-of-the-art methods in different testing strategies.