DCT-BP神经网络在表情识别中的应用  

The Application of DCT-Back Propagation Neural Network in Facial Expression Recognition

作　　者：杨霞[1] 潘晓露[1] 李一民[1] 王冲鶄[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650051

出　　处：《科技广场》2007年第3期143-145,共3页Science Mosaic

摘　　要：人脸表情识别作为智能化人机交互技术中的一个重要组成部分,近年来得到了广泛关注。本文提出了一种用DCT-BP神经网络算法来识别面部表情,先对图像进行灰度均衡和图像平滑的预处理,然后利用离散余弦变换获取图像的表情特征参数,最后利用前向反馈算法进行识别。As an important part of the technology for human-machine interface, facial expression recognition have drawn much attention recently. In this paper, we present an effective method ,which uses the discrete cosine transform （DCT and back propagation （BP） neutral network . First ,processing including normalization and filtering is carried out on facial images .Then discrete cosine transform is introduced. At last, recognition is made based on the back propagation neutral network.

关 键 词：表情识别 离散余弦变换 前向人工神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]