WANG Si-ming1,2, LIANG Yun-hua1,2
（1. School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China；2. Institute of Control Science and Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract：Local binary pattern (LBP) is an important method for texture feature extraction of facial expression. However, it also has the shortcomings of high dimension, slow feature extraction and noeffective local or global features extracted. To solve these problems, a facial expression feature extraction method is proposed based on improved LBP. Firstly, LBP is converted into double local binary pattern (DLBP). Then by combining Taylor expansion (TE) with DLBP, DLBP-TE algorithm is obtained. Finally, the DLBP-TE algorithm combined with extreme learning machine (ELM) is applied in seven kinds of ficial expression images and the corresponding experiments are carried out in Japanese adult female facial expression (JAFFE) database. The results show that the proposed method can significantly improve facial expression recognition rate.
Key words：facial expression feature extraction; DLBP-TE algorithm; computer vision; extrem learning machine (ELM)
CLD number：TP391.41 Document code：A
Article ID：1674-8042（2019）04-0342-06 doi：10.3969/j.issn.1674-8042.2019.04.006
References
［1］He L L. The effect of facial feedback on micro-expression recognition. Hunan: Hunan Normal University, 2014.
［2］Darwin C R, Ekman P. The expression of the emotions in man and animals. London: Harper Collins, 1998.
［3］Jeeman A K, Kamil Y. Analysis of local binary patterns for face recognition under varying facial expressions. In: Proceedings of 24th Signal Processing and Communication Application Conference, Zonguldak, Turkey, 2016: 2085-2088.
［4］Ekman P. Strong evidence for universals in facial expressions: a reply to Russell’s mistaken critique. Psychological Bulletin, 1994, 115(2): 268-287.
［5］Ekman P, Friesen W V. Facial action coding system: a technique for the measurement of facial movement. Palo Alto: Consulting Psychologists Press, 1978: 135-137.
［6］Timothy F C, Gareth J E, Christopher J T. Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685.
［7］Su Y. Modeling and matching of active apparent model. Xi’an: Xidian University, 2010: 4-8.
［8］Zhao H. Facial expression research based on face recognition technology. Harbin: Harbin University of Science and Technology, 2017: 30-35.
［9］Ojala T, Pietikanem M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 1996, 29(1): 51-59.
［10］Brian D R, Randolph L M. Taylor expansion of the differential range for monostatic SAR. IEEE Transactions on Aerospace and Electronic Systems, 2005, 41(1): 60-64.
［11］Wang L L, Liu J H, Fu X M. Facial expression recognition based on fusion of local feature and deep belief network. Laser & Optoelectronics Progress, 2018: 1-15.
基于改进LBP的人脸面部表情特征提取方法
王思明1,2， 梁运华1,2
（1. 兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070； 2. 兰州交通大学 控制科学与工程研究所， 甘肃 兰州 730070）
摘 要: 面部表情识别中， 局部二值模式(Local binary pattern, LBP)是一种重要的纹理特征提取方法， 但其在特征提取时维度较高、 提取速度慢、 不能得到有效的局部或者全局特征， 因而提出了一种基于改进LBP的人脸面部表情特征提取方法。 该将LBP转化为双局部二值模式(Double local binary pattern, DLBP)， 融合泰勒展开式(Taylor expansiion, TE)， 生成DLBP-TE算法， 此算法结合极限学习机(Extreme learning machine, ELM)分类算法应用于七种表情分类中， 在日本成年女性面部表情(JAFFE)数据库中进行实验。 结果表明， 此方法能显著提高面部表情识别率。
关键词: 面部表情特征提取； DLBP-TE算法； 计算机视觉； 极限学习机
引用格式： WANG Si-ming, LIANG Yun-hua. Facial expression feature extraction method based on improved LBP. Journal of Measurement Science and Instrumentation, 2019, 10（4）： 342-347. ［doi： 10.3969／j.issn.1674-8042.2019.04.006］
【full text view】
