[1]张雪梅,公维宾,邬建志,等.基于纹理特征融合的人脸表情识别[J].计算机技术与发展,2020,30(03):57-61.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 011]
　ZHANG Xue-mei,GONG Wei-bin,WU Jian-zhi,et al.Facial Expression Recognition Based on Texture Feature Fusion[J].Computer Technology and Development,2020,30(03):57-61.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 011]
点击复制

基于纹理特征融合的人脸表情识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年03期
页码:
57-61
栏目:
智能、算法、系统工程
出版日期:
2020-03-10

文章信息/Info

Title:
Facial Expression Recognition Based on Texture Feature Fusion
文章编号:
1673-629X(2020)03-0057-05
作者:
张雪梅; 公维宾; 邬建志; 王 超
长安大学 信息工程学院,陕西 西安 710064
Author(s):
ZHANG Xue-mei; GONG Wei-bin; WU Jian-zhi; WANG Chao
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
人脸表情识别; 局部二值模式; 韦伯局部描述符; 特征融合; 支持向量机
Keywords:
facial expression recognition; local binary mode; Weber local descriptor; feature fusion; support vector machine
分类号:
TP391.4
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 03. 011
摘要:
局部二值模式(LBP)和韦伯局部描述算子(WLD)是两种图像的纹理描述算子,在图像的特征提取方面有较强的 能力。 为了更加准确地对人脸表情进行识别与分类,针对 LBP在特征提取的过程中只考虑了中心像素点与周围的其他像 素点的灰度值之差,WLD 仅考虑中心像素点与周围像素点灰度值之间的激励强度与梯度方向关系的问题,提出一种新的 特征提取算法—局部二值韦伯模式(LBWP)。 首先对图像进行预处理,检验人脸和裁剪有效的表情区域,接着对图像进行 LBWP特征提取,在特征提取之后采用 SVM 的分类器对表情进行识别和分类。 该算法在 CK+ 数据集和 JAFFE 数据集上 进行实验仿真,识别率分别达到了97.14% 和 95.77%。 实验结果验证了 LBWP算法在表情识别方面的有效性,且丰富了人脸图像特征提取方法。
Abstract:
Local binary pattern(LBP) and Weber local descriptor(WLD) are two kinds of texture descriptors,which have strong ability in feature extraction.? ? ? ? ? In order to recognize and classify facial expressions more accurately,for these problems that LBP only considers the difference of gray value? between the center pixel and other surrounding pixels in the process of feature extraction,and WLD only considers the relation between the? ? intensity of excitation and the direction of gradient between the center pixel and the gray value of the surrounding pixel,a new feature extraction algorithm is proposed,which is local binary Weber model(LBWP). Firstly,the image is preprocessed to verify the face and clip effective expression area,and then the image is extracted with LBWP features. After feature extraction,the facial expression is recognized and classified by SVM classifier. The algorithm is simulated on CK+ dataset and JAFFE dataset,and the recognition rate reaches 97.14% and 95.77% respectively. Experimental results verify the effectiveness of LBWP in facial expression recognition,and enrich the face image feature extraction methods.

相似文献/References:

[1]张虎 方贤勇 吴忠标.基于多尺度细胞局部二值模式的人体检测[J].计算机技术与发展,2012,(07):52.
　ZHANG Hu,FANG Xian-yong,WU Zhong-biao.Human Detection Based on Multi-scale Cell Structured Local Binary Pattern[J].Computer Technology and Development,2012,(03):52.
[2]魏岩,涂铮铮,郑爱华,等.结合RGB颜色特征和纹理特征的消影算法[J].计算机技术与发展,2013,(10):72.
　WEI Yan,TU Zheng-zheng,ZHENG Ai-hua,et al.Shadow Elimination Algorithm of Combination of RGB Color Feature and Texture Feature[J].Computer Technology and Development,2013,(03):72.
[3]潘峥嵘,贺秀伟.人脸表情识别在智能机器人中的应用研究[J].计算机技术与发展,2018,28(02):173.[doi:10．3969/j．issn．1673－629X．2018．02．037]
　PAN Zheng-rong,HE Xiu-wei.Research on Application of Facial Expression Ｒecognition in Intelligent Ｒobot[J].Computer Technology and Development,2018,28(03):173.[doi:10．3969/j．issn．1673－629X．2018．02．037]
[4]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].Computer Technology and Development,2018,28(03):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[5]裴炜冬,朱铮涛,杨敏,等.基于改进的 Gabor 指纹纹理提取算法的研究[J].计算机技术与发展,2018,28(04):124.[doi:10.3969/ j. issn.1673-629X.2018.04.026]
　PEI Wei-dong,ZHU Zheng-tao,YANG Min,et al.Research on Texture Extraction Algorithm Based on Improved Gabor Fingerprint[J].Computer Technology and Development,2018,28(03):124.[doi:10.3969/ j. issn.1673-629X.2018.04.026]
[6]宋辉,刘奉华.基于数据预分析的虹膜识别方法[J].计算机技术与发展,2018,28(08):58.[doi:10.3969/ j. issn.1673-629X.2018.08.012]
　SONG Hui,LIU Feng-hua.An Iris Recognition Method Based on Data Pre-analysis[J].Computer Technology and Development,2018,28(03):58.[doi:10.3969/ j. issn.1673-629X.2018.08.012]
[7]白茹意.基于眼动仪和 LBP 的抽象画方向审美与识别[J].计算机技术与发展,2020,30(08):40.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 007]
　BAI Ru-yi.Aesthetics and Detection of Orientation of Abstract Painting Based on Eye Tracker and LBP[J].Computer Technology and Development,2020,30(03):40.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 007]
[8]付倩倩,李 昂.一种改进的卷积神经网络的表情识别算法[J].计算机技术与发展,2020,30(11):80.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 015]
　FU Qian-qian,LI Ang.An Improved Facial Expression Recognition Technology Based on Convolutional Neural Network[J].Computer Technology and Development,2020,30(03):80.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 015]
[9]王 珏,潘沛生.基于超分辨率重建的低分辨率表情识别的研究[J].计算机技术与发展,2021,31(07):47.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 008]
　WANG Jue,PAN Pei-sheng.Research on Low-resolution Facial Expression Recognition Based on Super-resolution Reconstruction[J].Computer Technology and Development,2021,31(03):47.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 008]
[10]孙维亚,陈科仲,李忠新,等.基于 LBP 特征的多视点目标分辨技术研究[J].计算机技术与发展,2021,31(09):43.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 008]
　SUN Wei-ya,CHEN Ke-zhong,LI Zhong-xin,et al.Research on Multi-view Target Resolution Based on LBP Characteristics[J].Computer Technology and Development,2021,31(03):43.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 008]

更新日期/Last Update: 2020-03-10