基于GLCM和CGA的人脸表情识别方法研究

Study of face expression recognition based on GLCM and CGA

提出基于灰度共生矩阵(GLCM)和混沌遗传优化算法(CGA)的人脸表情识别方法(FER)。为了消除遗传算法中个体在解空间内分布的不均匀性,利用混沌的随机性、遍历性和规律性,将混沌引入到遗传算法中,由此得到了混沌遗传优化算法(CGA);通过灰度共生矩阵提取出的特征和改进后的混沌遗传优化算法,将人脸表情识别的寻找感兴趣区域(ROI)和特征提取结合成一步;最后利用支持向量机(SVM)进行图像分类。理论和实验证明,该方法实现简单且切实可行。

A combined method of facial expression recognition （FER） is proposed based on gray level co-occurrence matrix （GLCM） and chaos in genetic algorithms （CGA）. Chaos in genetic algorithms is obtained by using randomness, ergodicity and regularity of chaos in order to solve the asymmetric of individual distributions in solution domain. Through the feature extraction by gray level co-occurrence matrix and chaos in genetic algorithm, an approach is proposed to solve the two tasks, searching region of interest selection （ROI） and feature extraction, simultaneously using a single evolving process. At last, SVM is applying to image classification. Reasoning by theory and experiment results, the method is computationally simple and feasible.