HOG描述符是旋转不变的？ [英] HOG descriptor is rotation invariant?

问题描述

我正在研究草杂草检测。我已经开始从HoG描述符中提取特征。正如HoG文献所研究的那样，HoG不是旋转不变的。我每种草杂草共有18幅图像，有两类。在我的训练和测试数据库中，我已经旋转了每个图像[5 10 15 20 ... 355]度。

I am working grass weed detection. I have started to extract features from the HoG descriptor. As studied from the HoG literature that the HoG is not rotation invariant. I have total 18 images of each class of grass weed and there is two classes. In my training and testing database I have rotated each image [5 10 15 20 ... 355] degree.

使用LibSVM程序包完成培训和测试。而且我的准确度大约为80％。

training and testing is done using LibSVM package. and I am getting accuracy of about 80%.

我的问题是，如果HoG不是旋转不变的，那么我怎样才能获得如此高的精度？

My question is if the HoG is not rotation invariant then how can I get such high accuracy?

推荐答案

首先，对于旋转不变的描述符D，你有：

D（图像）〜= D（image_5） 〜= D（image_X）

X：旋转角度

First thing first, for a rotationally invariant descriptor D you have :
D(image) ~= D(image_5) ~= D(image_X)
X : the angle of rotation

运算符〜=我们的意思是比较特征之间的距离很小。

By operator ~= we mean that the distance between the compared features is small.

因此，对于rotationnaly不变的描述符D，您不必将训练集添加到图像的旋转版本中。因为D（图像）〜= D（image_30）〜= D（图像_X），将旋转后的图像添加到训练集中是多余的（在特征空间中，您在非常相似的位置添加样本）。

As a consequence, for a rotationnaly invariant descriptor D, you don't have to add to your training set the rotated version of your image. Because D(image) ~= D(image_30) ~= D(image_X), adding the rotated image to the training set is somehow redundant (in the feature space you are adding samples at very similar position).

相反，在您的配置中，旋转的稳健性不是由HOG处理，而是通过：1 /数据增强（将旋转的图像添加到训练集） ）2 /机器学习算法SVM。
在特征空间中，对于HOG：D（图像）和D（图像_X）位于特征空间中的不同位置，并且SVM学会将它们放在同一类中。

Instead, in your configuration the robustness to rotation is not handled by HOG but by :
1/ data augmentation (adding the rotated images to the training set)
2/ the machine learning algorithm SVM.
In the feature space, for HOG : D(image) and D(image_X) are located in different positions in the feature space and the SVM learns to "put them" in the same class.

如果你真的想测试HOG对旋转的不变性，不要将旋转后的图像添加到训练集中，而是将它们保存在测试集中。准确度应该大幅下降。

If you really want to test the invariance of HOG against rotation, don't add the rotated images to the training set, but keep them in the test set. Accuraccy should fall drastically.

这篇关于HOG描述符是旋转不变的？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！