minHessian (Surffeaturedetector) 的解释

- 日理万妓 2022-08-20 06:21 29阅读 0赞

原文地址：[http://stackoverflow.com/questions/17613723/whats-the-meaning-of-minhessian-surffeaturedetector][http_stackoverflow.com_questions_17613723_whats-the-meaning-of-minhessian-surffeaturedetector]

原文内容：To decide if a pixel in an image is a SURF keypoint, an approximation of the Hessian matrix is built with the partial derivatives of the image intensities within a patch around the pixel. The determinant of this matrix is called Hessian and tells you how robust that pixel is as a blob center.

The `minHessian` is a threshold to decide from which value you are willing to accept keypoints. In practice, the higher the `minHessian`, the fewer keypoints you will obtain, but you expect them to be more repetitive (w.r.t. image transformations), and then, more useful. On the other hand, the lower the `minHessian`, the more keypoints you get, but they may be more noisy.

In usual images, a value between 400 and 800 works well.

Note that `SurfFeatureDetector` does not provide a way to select just a fixed number of keypoints. To do so, you have to set a low minHessian, sort the resulting keypoints by its Hessian value and then remove the least persistent ones.

翻译：为了判断一个点是否是surf特征点，需要在这个点周围构造一个hessian矩阵。决定这个矩阵的因素是hessian，它影响着特征点的鲁棒性。

minHessian是一个阈值，它决定了那些值是你接受的关键点。使用的时候，minHessian值越高，得到的关键点越少，但是关键点也就跟好。如果minHessian越小，得到的关键点会更多，但是关键点的质量也就不高。

一般，minHessian的值在400 和 800 之间。

注意：`SurfFeatureDetector` 并不会提供一个让你选择指定数目特征点的机会，你必须设定minHessian值，把关键点按Hessian值排序，然后去掉最不稳定的点。

[http_stackoverflow.com_questions_17613723_whats-the-meaning-of-minhessian-surffeaturedetector]: http://stackoverflow.com/questions/17613723/whats-the-meaning-of-minhessian-surffeaturedetector