基于特征优选和字典优化的组稀疏表示表情识别  

Group Sparse Representation Based on Feature Selection and Dictionary Optimization for Expression Recognition

作　　者：谢惠华 黎明[1,2] 王艳 陈昊[1,2] XIE Huihua;LI Ming;WANG Yan;CHEN Hao(School of Information Engineering,Nanchang Hangkong University,Nanchang 330063;Key Laboratory of Nondestructive Testing,Ministry of Education,Nanchang Hangkong University,Nanchang 330063)

机构地区：[1]南昌航空大学信息工程学院,南昌330063 [2]南昌航空大学无损检测技术教育部重点实验室,南昌330063

出　　处：《模式识别与人工智能》2021年第5期446-454,共9页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.61866025,61772255,61440049);江西省教育厅科学技术项目(No.GJJ170608);江西省研究生创新专项资金项目(No.YC2019-S339);江西省图像处理与模式识别重点实验室开放基金项目(No.ET201604246)资助。

摘　　要：针对在小样本人脸表情数据库上识别模型过拟合问题,文中提出基于特征优选和字典优化的组稀疏表示分类方法.首先提出特征优选准则,选择相同类级稀疏模式、不同类内稀疏模式的互补特征构建字典.然后对字典进行最大散度差优化学习,使字典在不失真重构特征的同时具有较高鉴别能力.最后联合优化后的字典进行组稀疏表示分类.在JAFFE、CK+数据库上的实验表明,文中方法对样本减少具有鲁棒性,泛化能力较强,识别精度较优.To solve the over-fitting problem of recognition model on small sample facial expression database,a group sparse representation classification method based on feature selection and dictionary optimization is put forward.Firstly,the feature selection criterion is proposed,and the complementary features of same class-level sparse mode and different intra-class sparse mode are selected to build a dictionary.Then,the dictionary is learned by maximum scatter difference optimization to reconstruct features without distortion and acquire a high discriminative ability.Finally,the optimized dictionary is combined for group sparse representation classification.Experiments on JAFFE and CK+databases show that the proposed method is robust to sample reduction with high generalization ability and recognition accuracy.

关 键 词：小样本表情识别 特征优选 最大散度差优化学习 组稀疏表示 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]