基于改进地形统计模型的表情识别  

AN IMPROVED STATIC TOPOGRAPHIC MODELING FOR FACIAL EXPRESSION RECOGNITION

作　　者：蒋海军[1] 赵晖[1] 

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046

出　　处：《计算机应用与软件》2011年第4期50-53,62,共5页Computer Applications and Software

基　　金：国家自然科学基金(60962005);新疆维吾尔自治区自然科学基金(200821124);教育部科学技术研究重点项目(208164);新疆高校科研计划青年教师启动基金项目(XJEDU2007509)

摘　　要：基于地形统计模型是一种新的有效的人脸表情特征提取方法,但还存在着一些问题,如图像大小不统一、忽略了局部信息、地形划分不够细致等。针对地形统计模型的人脸表情识别方法存在的问题,对表情人脸进行了宽度几何归一化处理;将地形特征与几何统计特征相融合;对粗略划分的地形进行了进一步的划分。实验显示方法能够有效地提高人脸表情的识别率。It is an innovative and effective method of facial feature extraction by building a statistic topographic model,but there are still some problems：the sizes of the images lack uniformity,the model misses local information,and the topographic maps in the model are not fine enough,etc.To deal with those problems,we conduct the generalisation of width geometry on the expression of the face;fuse the topographic features with geometric statistical features and make further partition based on the terrain maps which were roughly divided.Experiments prove that our method is able to improve the recognition rate of facial expression recognition effectively.

关 键 词：人脸表情识别 地形统计模型 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]