Face recognition by elastic bunch graph matching
Face recognition by elastic bunch graph matching
复制标题
DOI：
10.1109/icip.1997.647401
复制
发表时间：
1997-07
期刊：
影响因子：
--
通讯作者：
Laurenz Wiskott;J. Fellous;N. Krüger;C. Malsburg
中科院分区：
文献类型：
--
作者：
Laurenz Wiskott;J. Fellous;N. Krüger;C. Malsburg
我们提出了一个从包含每人一幅图像的大型数据库中从单幅图像中识别人脸的系统。人脸由基于Gabor小波变换的标记图表示。通过弹性图匹配过程提取新人脸的图像图，并通过简单的相似度函数进行比较。该系统与Lade等人的系统不同。(1993)在三个方面。利用相位信息对节点进行精确定位。对象适配图形用于处理深度较大的旋转。图像图的提取是基于一种新的数据结构--簇图，它是由一小部分样本图像图构成的。
We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from Lades et al. (1993) in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs.