问题描述
我目前正在一个项目中，我必须提取悲伤或快乐的用户的面部表情(一次从一个网络摄像头一次只有一个用户).
I am currently working on a project where I have to extract the facial expression of a user (only one user at a time from a webcam) like sad or happy.
我对面部表情进行分类的方法是:
My method for classifying facial expressions is:
- 使用opencv检测图像中的人脸
- 使用ASM和障碍物获取面部特征点
现在我正在尝试进行面部表情分类
and now i'm trying to do facial expression classification
SVM是一个不错的选择吗?如果可以的话，我该如何从SVM开始:
is SVM a good option ? and if it is how can i start with SVM :
我将如何使用这些地标为每种情感训练svm?
how i'm going to train svm for every emotions using this landmarks ?
推荐答案
是的，已经证明SVM在此任务中表现良好.已经有数十篇(如果不是杂乱无章的)论文描述了这种过程.
Yes, SVMs have been numerously shown to perform well in this task. There have been dozens (if not hundreads) of papers describing such procedures.
例如:
- Simple paper
- Longer paper
- Poster about it
- More complex example
可以在 http://www.support-vector-machines.org/(例如书名，软件链接等)
Some basic sources of the SVMs themselves can be obtained on http://www.support-vector-machines.org/ (like books titles, software links etc.)
如果您只是想使用它们而不是了解它们，那么您可以获取以下基本库之一:
And if you are just interested in using them rather then understanding you can get one of basic libraries:
- libsvm http://www.csie.ntu.edu.tw/~cjlin/libsvm/
- svmlight http://svmlight.joachims.org/
这篇关于使用SVM实时进行面部表情分类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！