融合全局与局部特征的单样本人脸识别

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:王科俊 邹国锋 阎涛

文章页码:760 - 764

关键词:全局特征;Gabor变换;局部特征;图像分块;加权并行集成

Key words:global feature; Gabor transformation; local feature; image block; weighted parallel integration

摘    要:分别通过双向二维主成分分析和Gabor特征分块提取人脸的全局特征和局部特征,提出一种将全局特征和局部特征分类结果在决策层并行集成的单样本人脸识别方法。ORL人脸库上的实验结果表明:经过Gabor特征分块的第一级融合和全局与局部特征的第二级融合能很好地融合人脸的全局和局部信息,提高人脸识别系统的 性能。

Abstract: A novel single sample face recognition algorithm based on parallel integration of classification results of the global and local features is proposed, where the global features are obtained by double two-dimensional principal component analysis and the local features are extracted by Gabor feature blocks. The experimental results on ORL face databases show that the global face and local information can be integrated well after the first level fusion by Gabor feature block and the second level fusion by global and local features, which improve the performance of face recognition system.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号