Semantic image segmentation in computer networks is designed to determine the category to which each pixel in an image belongs. It is a basic computer vision task and has a very wide range of applications in practice. In recent years, semantic image segmentation algorithms in computer networks based on deep learning have attracted widespread attention due to their fast speed and high accuracy. However, due to the large number of downsampling layers in a deep learning model, the segmentation results are usually poor at the edge of an object, and there is currently no universal quantitative evaluation index to measure the performance of segmentation at the edge of an object. Solving these two problems is of great significance to semantic image segmentation algorithms in China. Based on traditional evaluation indicators, this paper proposes a region-based evaluation index to quantitatively measure the performance of segmentation at the edge of an object and proposes an improved loss function to improve model performance. The existing semantic image segmentation methods are summarized. This paper proposes regional-based evaluation indicators. Taking advantage of the particularity of semantic image segmentation tasks, this paper presents an efficient and accurate method for extracting the edges of objects. By defining the distance from pixels to the edges of objects, this paper proposes a fast algorithm for calculating the edge area. Based on this, three methods are proposed as well as an area-based evaluation indicator. The experimental results show that the accuracy of the loss function proposed in this paper, compared with that of the current mainstream cross-entropy loss function, is improved by 1% on the DeepLab model. For area-based evaluation indicators, a 4% accuracy improvement can be achieved, and on other segmentation models, there is also a significant improvement.

中文翻译：

---

深度学习计算机网络中的语义图像分割算法

计算机网络中的语义图像分割旨在确定图像中每个像素所属的类别。它是一项基本的计算机视觉任务，在实践中有着非常广泛的应用。近年来，基于深度学习的计算机网络语义图像分割算法因其速度快、准确率高而受到广泛关注。但是，由于深度学习模型中下采样层数较多，物体边缘的分割效果通常较差，目前还没有通用的量化评价指标来衡量物体边缘的分割性能. 解决这两个问题对我国的语义图像分割算法具有重要意义。基于传统的评价指标，本文提出了一种基于区域的评估指标来定量衡量对象边缘分割的性能，并提出改进的损失函数以提高模型性能。总结了现有的语义图像分割方法。本文提出了基于区域的评价指标。本文利用语义图像分割任务的特殊性，提出了一种高效准确的对象边缘提取方法。本文通过定义像素到物体边缘的距离，提出了一种快速计算边缘面积的算法。在此基础上，提出了三种方法以及基于区域的评价指标。实验结果表明，本文提出的损失函数的准确性，与目前主流的交叉熵损失函数相比，在DeepLab模型上提高了1%。对于基于区域的评价指标，可以实现4%的准确率提升，在其他分割模型上，也有显着的提升。