如何使用LBP实施ICA以提高LBP的准确性，还是有其他方法可以改善它？ [英] How can I implement ICA with LBP to improve LBP's accuracy or is there other way to improve it?

问题描述

我们正在研究使用人脸识别的学生出勤率，我们正在使用LBP算法，但准确性很差，我们无法找到错误或做什么...



我尝试了什么：



我们尝试更改图像大小，以便训练和测试之间的区别不要是大的，但我们没有很好的结果...

We are working on aproject for student attendance using face recognition and we are using LBP algorithm but the accuracy is very bad, and we couldnt find whats wrong or what to do...

What I have tried:

We have tried changing the images sizes so that the difference between training and testing dont be larg but we didnt have good results...

推荐答案

通常我会建议使用 OpenCV库，如使用OpenCV进行面部和眼睛检测< / a>。



编写自己的算法是您的任务，您需要使用预期质量的数据进行调整。当您根据OpenCV的值检查代码时，您可能会发现一些问题。从一些简单而干净的案例开始，问题在哪些方面上升。这也有助于讨论结果有多好以及接下来要去哪里。



请记住：使用自己的算法有很多陷阱可靠性，通常是未知的边缘情况在黑暗中，宝贵的资源浪费在重新发明轮子而不是推动项目取得成功。

Normally I would recommand to use OpenCV library, used like in the article Face and Eyes Detection Using OpenCV .

When writing an own algorithm is your task, you need to tweak it mostly with the data in the expected quality. When you check your code against the values of OpenCV you may find some issues. Start it with some simple and clean cases to from which points the problems are rising. That also helps to discuss how good the results are and where to go next.

Remember: Using an own algorithm has a lot of pitfalls as reliability, often unknown edge case are in the dark and precious resources are wasted to "re-invent the wheel" instead of pushing the project to success.

这篇关于如何使用LBP实施ICA以提高LBP的准确性，还是有其他方法可以改善它？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！