新生儿疼痛面部表情识别方法的研究

卢官明; 李晓南; 李海波

光学学报, 2008, 28 (11): 2109, 网络出版: 2008-11-17

新生儿疼痛面部表情识别方法的研究

Research on Recognition for Facial Expression of Pain in Neonates

论文大纲

卢官明 ^1,*李晓南 ²李海波 ³

作者单位

¹ 南京邮电大学通信与信息工程学院, 江苏南京 210003

² 南京医科大学附属南京儿童医院, 江苏南京 210008

³ 瑞典于默奥大学应用物理与电子系, S-901 87 Ume, Sweden

摘要

针对新生儿的疼痛与非疼痛面部表情识别, 提出将Gabor变换和支持向量机(SVM)相结合的分类识别方法。对归一化后的大小为112 pixel×92 pixel的新生儿面部图像进行二维Gabor小波变换, 提取出 412160维Gabor特征; 针对Gabor 特征向量维数高、冗余大的特点, 采用Adaboost算法作为特征选择工具, 去除冗余的Gabor特征, 从412160 维特征中选取出900维Gabor特征; 对选取出的Gabor特征用SVM进行疼痛表情的分类识别。该方法综合运用Gabor 特征对于面部表情的良好表征能力、AdaBoost 算法的特征选择能力以及SVM 在处理少样本、高维数问题中的优势。对510幅新生儿的表情图像进行测试的结果表明, 疼痛与非疼痛表情的分类识别率达到85.29%, 疼痛与安静表情的分类识别率达到94.24%, 疼痛与哭表情的分类识别率达到78.24%。

Abstract

A classification method to distinguish the neonatal pain expression from non-pain expression is proposed, which combines Gabor wavelet transform with support vector machine (SVM). At first, each neonatal facial image, which is normalized to the size of 112 pixel×92 pixel, is transformed by the 2D Gabor wavelet to extract 412160 Gabor features. Since the high-dimensional Gabor feature vectors are quite redundant, AdaBoost is introduced as a feature selection tool to remove the redundant ones. In experiments, 900 features are selected from 412160 original Gabor features. Finally, the selected Gabor features are fed into the SVM for final classification. This method takes the advantages of the favorable ability of Gabor feature in representing facial expression, the effective function of Adaboost in feature selection, and the high performance of SVM in the solution to small sample size, high dimension problems. Experiments with 510 neonatal expression images show that the method is quite effective. The best recognition rates of pain versus non-pain (85.29%), pain versus calm (94.24%), pain versus cry (78.24%) are obtained.

参考文献

[1] . Grunau, Liisa Holsti, Jeroen W. B. Peters. Long-term consequences of pain in human neonates[J]. Seminars in Fetal & Neonatal Medicine, 2006, 11: 268-275.

[2] . J. S. Anada, V. Coskun, K. V. Thrivikraman et al.. Long-term behavioral effects of repetitive pain in neonatal rat pups[J]. Physiology & Behavior, 1999, 66(4): 627-637.

[3] . Lidow. Long-term effects of neonatal pain on nociceptive systems[J]. Pain, 2002, 99: 377-383.

[4] . Pain assessment: current status and challenges[J]. Seminars in Fetal & Neonatal Medicine, 2006, 11: 237-245.

[5] . J. W. Bours, Bonnie Stevens et al.. Assessment of pain in the neonate[J]. Seminars in Perinatology, 1998, 22(5): 402-416.

[6] . Measurement of neonatal responses to painful stimuli a research review[J]. J. Pain and Symptom Management, 1997, 14(6): 343-378.

[7] . Duhn, Jennifer M. Medves. A systematic integrative review of infant pain assessment tools[J]. Advances in Neonatal Care, 2004, 4(3): 126-140.

[8] . An exploration of nurses′ knowledge of, and attitudes towards, pain recognition and management in neonates[J]. J. Neonatal Nursing, 2005, 11: 65-71.

[9] . Fasel, Juergen Luettin. Automatic facial expression analysis: a survey[J]. Pattern Recognition, 2003, 36(1): 259-275.

[10] . Inferring facial expressions from videos: Tool and application[J]. Signal Processing: Image Communication, 2007, 22(9): 769-784.

[11] . Xiang, M. K. H. Leung, S. Y. Cho. Expression recognition using fuzzy spatio-temporal modeling[J]. Pattern Recognition, 2008, 41(1): 204-216.

[12] Irene Kotsia, Ioannis Pitas. Facial expression recognition in image sequences using geometric deformation features and support vector machines[C]. IEEE Transactions on Image Processing, 2007, 16(1): 172～187

[13] . Sebe, M. S. Lew, Y. Sun et al.. Authentic facial expression analysis[J]. Image and Vision Computing, 2007, 25(12): 1856-1863.

[14] Jun Wang, Lijun Yin. Static topographic modeling for facial expression recognition and analysis[J]. Computer Vision and Image Understanding, 2007, 108(1～2): 19～34

[15] Takeo Kanade, Jeffrey F. Cohn, Yingli Tian. Comprehensive database for facial expression analysis[C]. IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France, 2000. 46～53

[16] Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn. Recognizing action units for facial expression analysis[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 97～115

[17] Michael Lyons, Shigeru Akamatsu, Miyuki Kamachi et al.. Coding facial expressions with Gabor wavelets[C]. IEEE International Conference on Automatic Face and Gesture Recognition, 1998, A(14～16). 200～205

[18] Paul Ekman, Wallace V. Friesen. Facial Action Coding System: A Technique for the Measurement of Facial Movement[M]. Palo Alto, Calif.: Consulting Psychologists Press, 1978

[19] . Sexton et al.. Machine assessment of neonatal facial expressions of acute pain[J]. Decision Support Systems, 2007, 43(4): 1242-1254.

[20] . Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition[J]. IEEE Transactions on Image Processing, 2002, 11(4): 467-476.

[21] . Schapire. A decision-theoretic generalization of on-line learning and an application to boosting[J]. J. Computer and System Sciences, 1997, 55(1): 119-139.

[22] . Mutualboost learning for selecting Gabor features for face recognition[J]. Pattern Recognition Letters, 2006, 27(15): 1758-1767.

[23] 陈全胜, 赵杰文, 张海东. 基于支持向量机的近红外光谱鉴别茶叶的真伪[J]. 光学学报, 2006, 26(6): 933～937

Chen Quansheng, Zhao Jiewen, Zhang Haidong. Identification of authe nticity of tea with near infrared spectroscopy based on support vector machine[J] . Acta Optica Sinica, 2006, 26(6): 933～937

[24] 叶美盈, 汪晓东. 混沌光学系统辨识的支持向量机方法[J]. 光学学报, 2004, 24(7): 953～956

Ye Meiying, Wang Xiaodong. Identification of chaotic optical system based on support vector machine[J]. Acta Optica Sinica, 2004, 24(7): 953～956

[25] 李素梅, 韩应哲, 张延炘. 基于支持向量机的非线性荧光光谱的识别[J]. 光学学报, 2006, 26(1): 147～151

Li Sumei, Han Yingzhe, Zhang Yanxin. Recognition of nonlinear fluorescence spect rum of support vector machine networks[J] . Acta Optica Sinica, 2006, 26(1): 147～151

卢官明, 李晓南, 李海波. 新生儿疼痛面部表情识别方法的研究[J]. 光学学报, 2008, 28(11): 2109. Lu Guanming, Li Xiaonan, Li Haibo. Research on Recognition for Facial Expression of Pain in Neonates[J]. Acta Optica Sinica, 2008, 28(11): 2109.

新生儿疼痛面部表情识别方法的研究

关于本站 Cookie 的使用提示

全站搜索

新生儿疼痛面部表情识别方法的研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索