Human Mouth-State Recognition Based on Image Warping and Sparse Representation Combined with Homotopy  

作　　者：李翠梅 曾萍萍 朱劲强 吴建华 

机构地区：[1]School of Communication and Electronics,Jiangxi Science & Technology Normal University [2]College of Science and Technology,Nanchang University [3]Department of Electronic Information Engineering,Nanchang University

出　　处：《Journal of Donghua University(English Edition)》2015年第4期658-664,共7页东华大学学报（英文版）

基　　金：National Natural Science Foundation of China(No.61210306074);Natural Science Foundation of Jiangxi Province,China(No.2012BAB201025);the Scientific Program of Jiangxi Provincial Education Department,China(Nos.GJJ14583,GJJ13008)

摘　　要：It is often necessary to recognize human mouth-states for detecting the number of audio sources and improving the speech recognition capability of an intelligent robot auditory system. A human mouth-state recognition method based on image warping and sparse representation( SR) combined with homotopy is proposed.Using properly warped training mouth-state images as atoms of the overcomplete dictionary overcomes the impact of the diversity of the mouths' scales,shapes and positions so that further improvement of the robustness can be achieved and the requirement for a large number of training samples can be relieved. The homotopy method is employed to compute the expansion coefficients effectively,i. e.,for sparse coding. The orthogonal matching pursuit( OMP) is also tested and compared with the homototy method. Experimental results and comparisons with the state-of-the-art methods have proved the effectiveness of the proposed approach.It is often necessary to recognize human mouth-states for detecting the number of audio sources and improving the speech recognition capability of an intelligent robot auditory system. A human mouth-state recognition method based on image warping and sparse representation（ SR） combined with homotopy is proposed.Using properly warped training mouth-state images as atoms of the overcomplete dictionary overcomes the impact of the diversity of the mouths＇ scales,shapes and positions so that further improvement of the robustness can be achieved and the requirement for a large number of training samples can be relieved. The homotopy method is employed to compute the expansion coefficients effectively,i. e.,for sparse coding. The orthogonal matching pursuit（ OMP） is also tested and compared with the homototy method. Experimental results and comparisons with the state-of-the-art methods have proved the effectiveness of the proposed approach.

关 键 词：mouth-state recognition image warping sparse representation(SR) sparse coding HOMOTOPY 

分 类 号：TN911.73[电子电信—通信与信息系统] O235[电子电信—信息与通信工程]