我正在尝试制作一个可以检测面部并识别它的应用程序。我做了人脸检测，但我想在识别时得到一些想法。我正在使用网络摄像头进行跟踪，它可以检测脸部。然后，我仅将脸部的一部分与新的灰色图像进行比较，并使用 EigenObjectRecognizer 将其与数据库中的图像列表进行比较。
但它并没有给出好的结果。有时它发现有什么问题，有时什么也没有。我想问一下，为了比较照片，我必须实施哪些附加技术？像直方图均衡或面部分辨率均衡？
I am trying to make an app that detect faces and recognizes it. I made Face detection but I want some idea to when making recognition. I'm using a web cam for tracking and it can detect the face.Then I am taking only the part of the face to a new gray image and comparing it using EigenObjectRecognizer with list of images in database.
But it is not giving good results. Some times it find some thing wrong, some times nothing. I want to ask that for comparing photos which additional techniques I must implement? Like Histogram equalization or resolution of faces equalization?
发布评论
评论（4）
我有一个 OpenCV 人脸识别（Haar 人脸检测 + 直方图均衡 + Eigenfaces）教程和免费源代码，您可以尝试：
http://www.shervinemami.info/faceRecognition.html
I have an OpenCV Face Recognition (Haar Face Detection + Histogram Equalization + Eigenfaces) tutorial and free source code that you could try:
http://www.shervinemami.info/faceRecognition.html
人脸检测和人脸分类是完全不同的问题。根据我的经验和阅读几篇有关人脸分类的论文，我可以告诉您，一个好的开始方法是阅读主成分分析（PCA，也称为特征脸）、费舍尔线性判别分析（LDA）和支持向量机（支持向量机）。这些分类方法对于人脸分类非常有用，事实证明 OpenCV 已经在 PCA 和 SVM。 此网站是 C++ 中 OpenCV 人脸识别和分类代码的绝佳资源。
这个是一个网站，它提供了大多数人脸分类相关方法的资源和论文链接。
一个很好解释的 PCA Eigenfaces 和 LDA 示例，在 Matlab 中包含示例代码，这对于我的第一个面部分类程序非常有用 在这里。
Face detection and face classification are completely different problems. I can tell you from my experience and from reading several papers on face classification, that a good way to start is by reading about Principal Component Analysis (PCA also known as Eigenfaces), Fisher's Linear Discriminant Analysis (LDA), and Support Vector Machines (SVMs). These are classification methods that are extremely useful for face classification, and it turns out that OpenCV already includes excellent implementations on PCA and SVM. An excellent resource for face recognition and classification code for OpenCV in C++ is this website.
One website that offers resources and links to papers for most relevant methods for face classification is this one.
A well explained example of PCA Eigenfaces and LDA with sample code in Matlab that was extremely useful for my first face classification program is here.
特征脸只会让你在人脸识别方面走得更远。您可以训练的面孔数量是有限的。您必须研究更新的算法，查看该领域的新论文并实现它们。
您可以通过确保所有图像具有相同的方向和大小来实现特征脸的效率。方向和位置非常重要。因此，请确保在比较之前应用正确的转换
Eigenfaces will only get you so much further in face recognition. There's a limit with the number of faces you can train. You'll have to look into newer algorithms , check out new papers in this field and implement them.
You can implement the efficiency of Eigenfaces by making sure that all your images are of the same orientation and size. Orientation and position matters a lot. So make sure you apply right transformations before comparison
请通过下面的链接查看我的答案。里面有一些链接会对你有帮助，主要是我提到的 YouTube 视频。
骰子面值识别
Check my answer at the link below. There are some links in it that will be helpful to you, mainly the YouTube video I mentioned.
Dice face value recognition