Semantic description method for face features of larger Chinese ethnic groups based on improved WM method

In this paper, a semantic description method based on improved WM algorithm is proposed to characterize the facial features of larger Chinese ethnic groups. We firstly utilize the face landmarking technique to extract facial feature points automatically. Geometric features are defined with these detected landmarks, including distances, perimeters and areas. Then the WM method is improved to generate linguistic rule from facial geometric feature data, which implements semantic description for multi-ethnic facial characteristics. Finally, a case study of learning ethnicity from face with proposed method is investigated in CEFD database. The experiment results indicate that the linguistic rule base obtained by method is competitive in ethnicity recognition compared with method Naive Bayes, C4.5, Decision Table, Random Forest, Adaboost and Logistic regression in terms of accuracy and interpretability.