Face Expression Recognition Using a Combination of Local Binary Patterns and Local Phase Quantization

Facial expressions are the first communication channel in human interactions. This channel helps us to understand people thoughts. The accuracy of the knowledge that have obtained by this channel benefits us in decision-making stages. Therefore, many studies in this domain are conducted for the accurate face expression recognition (FER) systems. In order to establish a robust and reliable FER system, it is a requirement to have the informative facial image features. In this study, it is used Local Binary Patterns (LBP) and Local Phase Quantization (LPQ) methods to establish a reliable FER approach. The main goal is to determine whether combining these two methods makes a contribution or not. Experiments show that combining these two methods increases the classification success rate from 75% to 88%.