图像分割结果中的噪声 [英] noise in image segmentation result

问题描述

我正在做一个基于深度卷积神经网络的图像分割任务。网络结构来自本文，结构如图所示：用于图像分割的FCN 。该网络基于完全卷积网络和 DCAN 。

I am doing a image segmentation task based on deep convolutional neural network. The network structure is from this paper, and the structure can be seen in the picture:FCN used in image segmentation. The network is designed based on Fully Convolutional Network and DCAN.

该数据集是Gland Segmentation Chalenge Contest的公共基准数据集在 MICCAI 2015 （也称为Warwick-QU数据集。）

The data set is the public benchmark dataset of Gland Segmentation Chalenge Contest in MICCAI 2015(also named as Warwick-QU dataset.)

我使用此网络执行分段任务。然而在我的结果中，我总是注意到一个固定的噪音模式：预测图像中的小白色交叉：具有交叉形状噪声的预测结果

I use this network to do the segmentation task. However in my result, I always noticed a fixed pattern of noise: the little white crossing in the predicted image:Prediction results with crossing shape noise

有人可以解释这些噪声像素的含义吗？它们是图像处理中常见的噪音吗？值得注意的是，这种现象不仅出现在特定的图像中，而且出现在整个预测中。

Can someone please explain what does these noise pixels mean? Are they the common noises in image processing? It is worth noting that this phenomena does not appear only in a specific image, but for the whole prediction.

推荐答案

这些现象 - 形状噪声是由我网络中的反卷积层引起的，它通过改变解卷积层中的内核大小来解决。

These crossing-shape noises are caused by the deconvolutional layer in my network, and it is solved by changing the kernel size in deconvolutional layer.

首先我们应该了解deconvolutonal层是如何工作的。可以在此处找到清晰的图示。我们需要记住的是，解卷积中的步幅有助于放大特征贴图的大小。

First we should understand how does the deconvolutonal layer work. A clear illustration can be found here. What we need to bear in mind is that the stride in deconvolution helps to enlarge the size of the feature map.

回到这个例子。假设我们有一个 32x32 的特征图，我们希望获得大小为 256x256 的特征图，所以我们必须使用具有<步长<的去卷积层强> 8x8 进行反卷积，因此很多零像素被添加到特征图中，这就是为什么会出现这种交叉形状的原因。为了解决这个问题，我们必须将内核大小扩大两倍。在上面的示例中，我们需要选择 16x16 内核，以便我们的过滤器不会落入这些零。

Back to this example. Let's say we have a feature map of 32x32 and we want to get the feature map with the size of 256x256, so we have to use the deconvolutional layer with a stride of 8x8 to do the deconvolution, thus a lot of zero pixels are added to the feature map, that is why these crossing shape occurs. To deal with this, we have to enlarge our kernel size twice as the stride. In the above example we need choose a 16x16 kernel so that our filter will not fall into those zeros.

结果图像可以在这里显示：结果

我们可以清楚地看到，与问题中附带的图片相比，交叉形状的噪音被删除了。

The result image can be shown here: result
We can see clearly that the crossing-shape noises are removed compared with the picture attached in the question.

这篇关于图像分割结果中的噪声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！