SIFT 中的边缘响应去除
在 Lowe 的论文第 4.1 节中，使用 Hessian 矩阵的主曲率比率用于消除可能属于边缘的点。
论文没有具体说明Hessian矩阵是在原始图像上计算还是在DoG上计算。在Rob Hess 的实现中，它被应用在指定八度音阶的 DoG 上。间隔。
我的问题是为什么在 DoG 上应用 Hessian 矩阵来识别潜在边缘的点？
我从Utkarsh的教程中了解到< /a> Hessian 应该与 Harris 角点检测类似。不同的是Hessian矩阵是二阶导数。所以我得出的结论是应该将 Hessian 应用于原始图像。
您能给我指出解释如何使用 Hessian 的相关资源吗？
In Lowe's paper Section 4.1 the ratio of principal curvatures using the Hessian Matrix is used to eliminate points that may belong to an edge.
The paper does not specify whether the Hessian matrix is computed on the original image or the DoG. In Rob Hess's implementation it is applied on the DoG at the specified octave & interval.
My question is why is the Hessian Matrix applied on the DoG to identify points that are potential edges?
I understand from Utkarsh's tutorial that the Hessian is supposed to be similar to Harris corner detection. The difference is that the Hessian matrix is a second-order derivative. So I concluded that the Hessian should be applied to the original image.
Can you point me to relevant resources that explain how the Hessian is used?
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（1）
SIFT 论文表明 Hessian 矩阵计算的输入确实是 DoG。 DoG 不是边缘图，因为它不是二进制的。然而，它消除了噪音并突出了 DoG 的该级别中显示的功能。因此，从本质上讲，DoG 的高值像素是该级别需要处理的最重要的特征。
谢谢。
The paper on SIFT indicates that the input to the Hessian matrix calculation is indeed the DoG. The DoG is not an edge map because its not binary. However, it has eliminated noise and accentuates features that show up in that level of the DoG. So in essence, the high value pixels of the DoG are the most important features to be worked with at that level.
Thanks.