简体繁体 English

人脸识别模型准确性低

[英]Low accuracy in facial recognition model

原文 2018-08-06 06:30:59 2 1 python/ face-recognition

I am running the code provided by Adrian in this link https://www.pyimagesearch.com/2018/06/25/raspberry-pi-face-recognition/#comment-473194 . 我正在此链接https://www.pyimagesearch.com/2018/06/25/raspberry-pi-face-recognition/#comment-473194中运行Adrian提供的代码。 I have a dataset containing 6 faces of 3 people each. 我有一个数据集，其中包含3个人的6张面孔。 I ran this code and it works fine when detecting my face and my friend's face. 我运行了这段代码，当检测到我的脸和朋友的脸时，它可以正常工作。 It faces trouble while detecting the third person's face. 在检测到第三者的脸部时会遇到麻烦。 It detects it as my face. 它检测到它是我的脸。 Does this algorithm work only for binary classification? 该算法仅适用于二进制分类吗？ Will the accuracy improve if I improve if I make the dataset bigger? 如果我将数据集扩大到更大的范围，准确性会提高吗？

1 个解决方案

If you increase your database. 如果增加数据库。 It will increase the accuracy for sure. 肯定会提高准确性。 Also opencv is not a good solution if you want to detect a face in real time for the sake of accuracy.Cause, when an object is moving, then the cascade function shows some kind of miss classification. 如果您想实时检测人脸以确保准确性，opencv也不是一个很好的解决方案。原因是当对象移动时，级联函数会显示某种未分类的情况。

However you can use dlib function to make your processing robust. 但是，您可以使用dlib函数使您的处理更可靠。 Or you can use yolo for face recognition. 或者，您可以使用yolo进行面部识别。