基于多图像组信息的人脸识别研究

提出利用多图像组信息构建二部学习框架进行人脸识别。首先,利用两种不同的多图像组信息源分别学习两个相应的度量空间模型;其次,将得到的模型合并为一个统一的判别距离度量空间;最后,对所构建的二部学习框架进行范化,使得框架中的多图像组信息能够用来进行子空间学习和距离度量学习。通过在多个标准通用数据集上得到实验结果验证了所提出方法的有效性。

Face Recognition based on Group Information of Multiple Images

In this paper, we propose a bipart framework to take advantage of group information of multiple images of each subject in the testing set as well as in the training set. Two different sources of group information of multiple images which are utilized to learn two metric space models independently are combined to form a unified discriminative distance space. Furthermore, the bipart framework is generalized to allow both subspace learning and distance metric learning methods to take advantage of this group information. The proposed framework is evaluated on the face recognition problem using several benchmark datasets, which demonstrates the validity.