定向梯度直方图与边缘定向直方图 [英] Histogram of Oriented Gradients vs Edge Orientation Histograms

问题描述

我不清楚HOG和EOH之间的区别。 Hog基于图像导数EOH基于边缘方向。看起来HOG也以某种方式表示EOH。

I am not clear about the difference between the HOG and EOH. Hog is based on image derivatives EOH is based on edge directions. It seems that HOG also somehow a representation of EOH.

您能给我一些解释EOH与HOG的区别，以及EOH与HOG的优点。在什么情况下我们可以使用EOH与HOG比较？

Could you please give me some explanation about how EOH differs from HOG and the advantages over EOH compare to HOG. In what circumstances we can use EOH compare to HOG?

推荐答案

我认为主要的区别是，对于HOG，方向，然后进行分箱，其中对于EOH，通过搜索一组边缘过滤器内核的最大响应来评估边缘取向。所以你可以说HOG在梯度计算之后进行分级，其中EOH直接计算分级中的梯度。

I think the main difference is that for a HOG, the actual gradient direction is calculated and then binned, where for an EOH the edge orientation is evaluated by searching the maximum response over a set of edge filter kernels. So you could say that HOG does the binning after the gradient computation, where EOH directly calculates the gradient in bins. Depending on the amount of bins you want, one will be faster than the other.

在EOH中，浅色 - 深色和深色的边缘通常被视为相同的，取向因此在0至π的范围内，其中在HOG中，箱通常跨越整个2 *π。你可以很容易地让EOH这样做。

In an EOH, light-dark and dark-light edges are usually treated the same and the orientations are therefore in a range of 0 to pi, where in a HOG the bins usually span a full 2*pi. You can easily make an EOH do this too however.

这篇关于定向梯度直方图与边缘定向直方图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IT屋！