Facial expression recognition using constructive feedforward neural networks
Facial expression recognition using constructive feedforward neural networks
复制标题
DOI：
10.1109/tsmcb.2004.825930
复制
发表时间：
2004-06-01
影响因子：
--
通讯作者：
Khorasani, K
中科院分区：
文献类型：
--
作者：
Ma, L;Khorasani, K
提出了一种新的人脸表情识别方法，该方法利用整幅人脸图像的二维离散余弦变换（DCT）作为特征检测器，利用构造性单隐层前馈神经网络作为表情分类器。一个输入端修剪技术，提出了作者以前，也被纳入建设性的学习过程中，以减少网络的大小，而不牺牲所得到的网络的性能。所提出的技术被应用到一个数据库中的60名男子的图像，每个有五个面部表情图像（中性，微笑，愤怒，悲伤和惊喜）。40名男性的图像用于网络训练，其余20名男性的图像用于泛化和测试。在网络训练和泛化四个面部表情（微笑，愤怒，悲伤和惊讶）计算的混淆矩阵被用来评估训练后的网络的性能。结果表明，最好的识别率为100%和93.75%（无拒识），分别为训练和推广的图像。此外，所构建的网络的输入侧权重减少了约30%，使用我们的修剪方法。与文献中基于固定结构反向传播的识别方法相比，该方法构造了一个隐层前向神经网络，隐层单元数和权值均减少了d，同时提高了泛化能力和识别性能。
A new technique for facial expression recognition is proposed, which uses the two-dimensional (2-D) discrete cosine transform (DCT) over the entire face image as a feature detector and a constructive one-hidden-layer feedforward neural network as a facial expression classifier. An input-side pruning technique, proposed previously by the authors, is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having five facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images of 20 men are used for generalization and testing. Confusion matrices calculated in both network training and generalization for four facial expressions (smile, anger, sadness, and surprise) are used to evaluate the performance of the trained network. It is demonstrated that the best recognition rates are 100% and 93.75% (without rejection), for the training and generalizing images, respectively. Furthermore, the input-side weights of the constructed network are reduced by approximately 30% using our pruning method. In comparison with the fixed structure back propagation-based recognition methods in the literature, the proposed technique constructs one-hidden-layer feedforward neural network with dfewer number of hidden units and weights, while simultaneously provide improved generalization and recognition performance capabilities.