摘要
提出了小波变换技术和模糊神经网络技术相结合的人脸识别方法。小波变换具有良好的多尺度特征表达能力,能将图像的大部分能量集中到最低分辨率子图像,高频部分则对应于图像的边缘和轮廓,能很好的表征人脸图像的特征。模糊神经网络具有很强的分类能力,并且可以运用神经网络的学习算法。实验表明,二者的结合对人脸识别具有计算量小,识别率高的优点,有很强的实用性。
This paper introduces a method of face recognition based on wavelet transform and fuzzy neural network. Wavelets transform has a good ability to express the multi-resolution characteristics.After the wavelets transform of an image, its most energy is mainly concentrated on its lowest resolution and the boundary and profile of the image are contained in the high frequency part, The fuzzy neural network is of the robust classification ability and can be trained by neural algorithm. The experimental results exhibit the effectiveness and robust of the method.
出处
《机电产品开发与创新》
2006年第2期32-34,共3页
Development & Innovation of Machinery & Electrical Products
基金
湖南省教育厅自然科学基金资助项目(04C476
05C141)
关键词
人脸识别
小渡变换
BP网络
face recognition
wavelet transform
fuzzy neural network
