In the field of visual perception, the edges of images tend to be rich in effective visual stimuli, which contribute to the neural network’s understanding of various scenes. Image smoothing is an image processing method used to highlight the wide area, low-frequency components, main part of the image or to suppress image noise and high-frequency interference components, which could make the image’s brightness smooth and gradual, reduce the abrupt gradient, and improve the image quality. At present, there are still problems such as easy blurring of the edges of the image, poor overall smoothing effect, obvious step effect, and lack of robustness to noise on image smoothing. Based on the convolutional neural network, this article proposes a method for edge detection and deep learning for image smoothing. The results show that the research method proposed in this article solves the problem of edge detection and information capture better, significantly improves the edge effect, and protects the effectiveness of edge information. At the same time, it reduces the signal-to-noise ratio of the smoothed image and greatly improves the effect of image smoothing.

中文翻译：

---

一种新的基于卷积神经网络的图像边缘平滑方法

在视觉感知领域，图像边缘往往富含有效的视觉刺激，有助于神经网络对各种场景的理解。图像平滑是一种图像处理方法，用于突出图像的大面积、低频成分、主要部分或抑制图像噪声和高频干扰成分，使图像的亮度平滑渐变，减少突变的梯度，并提高图像质量。目前还存在图像边缘容易模糊、整体平滑效果差、阶梯效应明显、图像平滑对噪声缺乏鲁棒性等问题。本文基于卷积神经网络，提出了一种边缘检测和深度学习的图像平滑方法。结果表明，本文提出的研究方法较好地解决了边缘检测和信息捕获问题，显着改善了边缘效果，保护了边缘信息的有效性。同时降低了平滑图像的信噪比，大大提高了图像平滑的效果。