Legendre moments for face identification based on single image per person
Legendre moments for face identification based on single image per person
复制标题
基于单张图像的人脸识别勒让德矩
DOI：
10.1109/icsps.2010.5555580
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
J. Mohammadi
中科院分区：
文献类型：
--
作者：
R. Akbari;Mehdi Keshavarz Bahaghighat;J. Mohammadi
当前人脸识别技术面临的主要挑战之一在于样本采集困难。每人样本越少，意味着收集样本的费力就越少，存储和处理成本也就越低。不幸的是，许多报道的人脸识别技术严重依赖于训练集的大小和代表性，如果系统只有每人一个训练样本，大多数人脸识别技术都会遭受严重的性能下降，甚至无法工作。本文提出了一种基于勒让德矩特征向量的识别算法，尝试解决单图像问题。我们的实验中使用了 FERET 数据库中的 200 张图像和 AR 数据库中的 100 张图像。本文报告的结果表明，所提出的方法对 AR 和 FERET 的准确率分别为 91% 和 89.5%。
One of the main challenges faced by the current face recognition techniques lies in the difficulties of collecting samples. Fewer samples per person mean less laborious effort for collecting them, lower cost for storing and processing them. Unfortunately, many reported face recognition techniques rely heavily on the size and representative of training set, and most of them will suffer serious performance drop or even fail to work if only one training sample per person is available to the systems. In this paper, a recognition algorithm based on feature vectors of Legendre moments is introduced as an attempt to solve the single image problem. Subset of 200 images from FERET database and 100 images from AR database are used in our experiments. The results reported in this paper show that the proposed method achieves 91% and 89.5% accuracy for AR and FERET, respectively.