| 基于CBP-TOP特征的人脸表情识别* |
| |
| 引用本文： | 朱勇,詹永照. 基于CBP-TOP特征的人脸表情识别*[J]. 计算机应用研究, 2011, 28(5): 1957-1960. DOI: 10.3969/j.issn.1001-3695.2011.05.103 |
| |
| 作者姓名： | 朱勇 詹永照 |
| |
| 作者单位： | 江苏大学,计算机科学与通信工程学院,江苏,镇江,212013 |
| |
| 基金项目： | 国家自然科学基金资助项目 |
| |
| 摘 要： | 针对人脸表情时空域特征信息的有效提取，本文提出了一种CBP-TOP（Centralized Binary Patterns From Three Orthogonal Panels）特征和SVM分类器相结合的人脸表情识别新方法。该方法首先将原始图像序列进行图像预处理，包括人脸检测、图像截取和图像尺度归一化，然后用CBP-TOP算子对图像序列进行分块提取特征，最后采用SVM分类器进行表情识别。实验结果表明，该方法能更有效提取图像序列的运动特征和动态纹理信息，提高了表情识别的准确率。和VLBP特征相比， CBP-TOP特征在表情识别中具有更高的识别率和更快的识别速度。
|
| 关 键 词： | 人脸表情识别；人脸检测；尺度归一化；CBP-TOP特征 |
| 收稿时间： | 2010-10-12 |
| 修稿时间： | 2010-11-07 |
Facial expression recognition based on CBP-TOP features |
| |
| ZHU Yong,ZHAN Yong-zhao. Facial expression recognition based on CBP-TOP features[J]. Application Research of Computers, 2011, 28(5): 1957-1960. DOI: 10.3969/j.issn.1001-3695.2011.05.103 |
| |
| Authors: | ZHU Yong ZHAN Yong-zhao |
| |
| Affiliation: | ZHU Yong,ZHAN Yong-zhao(School of Computer Science & Telecommunication Engineering,Jiangsu University,Zhenjiang Jiangsu 212013,China) |
| |
| Abstract: | According to effective extraction of facial expression information in space-time domain,this paper proposed a novel approach for facial expression recognition based on CBP-TOP features and SVM classifier.In this method,processed original image sequences first,including face detection,image interception and size normalized.Then extracted the features of image from the blocks of images using the CBP-TOP operator.Finally recognized six expressions by support vector machine classifier.The experiment result show... |
| |
| Keywords: | facial expression recognition face detection size normalized CBP-TOP features |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
