Philippine E-Journals

An MSULBP Features Selection based on GA and Majority Voting Mechanism in Facial Expression Recognition

Jafar Sheykhzadeh | Akhtar Hazrati Bishak | Mohammad Bagher Moradi Gheshlagh

 

Abstract:

Because of excellent capability of description of local texture, local binary patterns (LBP) have been applied in many areas. Also, to extract individual features the efficacy of the uniform LBP has been validated. In this study, a proposed new facial expression recognition system based on Multi-Scale Uniform LBP (MSULBP) schema can fully utilize LBP information. In the previous works, the selection of the optimal subset of the extracted features has not been considered. But in the proposed algorithm, the MSULBP features were extracted from the original facial expression images. The best subset from MSULBP features was found by genetic algorithm (GA) and majority voting mechanism (MVM) and was represented as a histogram descriptor. Finally, support vector machines (SVM) classifier was used for facial expression classification. The experimental results on the popular Japanese female facial expression (JAFFE) database illustrate that the presented facial expression recognition method based on MSULBP obtains the best recognition accuracy rate. Additionally, experiments show that the MSULBP features are robust to low-resolution images, which is critical in real-world applications.