如何自适应地添加和使用鉴权时采集的人脸图像来提高人脸鉴权的性能? [英] How to adaptively add and use face images collected while authentication to improve performance of face authentication?

问题描述

我目前的项目是建立一个人脸认证系统.我的限制是:在注册期间，用户提供单个图像进行训练.但是，我可以在身份验证时添加和使用用户提供的图像.

My current project is to build a face authentication system. The constraint I have is: during enrollment, the user gives single image for training. However, I can add and use images given by the user while authentication.

我想在训练中添加更多图像的原因是，用户环境不受限制 - 不同的照明条件，与相机的不同距离，来自不同的 MP 相机.唯一的缓解是姿势几乎是正面的.

The reason I want to add more images into training is, the user environment is not restricted - different lighting conditions, different distance from camera, from different MP cameras. The only relief is the pose is almost frontal.

我认为，上述问题类似于广泛使用的面部标记应用程序.任何人都可以提出一种自适应和智能地使用可用图像的方法吗?

I think, the above problem is similar to the face tagging app widely available. Can anyone suggest a method to use the available images adaptively and smartly??

--谢谢

推荐答案

我建议你仔细看看 SOM(self-organizing maps).我认为它包含了您提到的所有问题和限制的解决方案.

I would recommend that you give SOM(self-organizing maps) a close look. I think it contains the solutions to all the problems and constraints you have mentioned.

您可以将它用于每个人的单个图像问题.此外，使用多 SOM 面策略，您可以在有更多图像可用于训练的情况下对其进行调整.整个概念的巧妙之处在于，当遇到新面孔时，只需要重新学习新面孔，而不是整个原始数据库.

You can employ it for the single image per person problem. Also, using the multiple SOM-face strategy, you can adapt it for cases when additional images are available for training. Whats pretty neat about the whole concept is that when a new face is encountered, only the new one rather than the whole original database is needed to be re-learned.

在此过程中您可能会发现一些有用的链接:

A few links which you might find helpful along the way:

http://en.wikipedia.org/wiki/Self-organizing_map (维基)

http://cs.nju.edu.cn/zhouzh/zhouzh.files/publication/tnn05.pdf(一篇有趣的研究论文，展示了上述技术)

http://cs.nju.edu.cn/zhouzh/zhouzh.files/publication/tnn05.pdf (An interesting research paper which demonstrates the above mentioned technique)

祝你好运

这篇关于如何自适应地添加和使用鉴权时采集的人脸图像来提高人脸鉴权的性能?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！