TY -的A2 -叮,白元盟- Fu,徐汇PY - 2021 DA - 2021/12/10 TI -中国古代模式修复的研究和应用基于深卷积神经网络SP - 2691346六世- 2021 AB -近年来,深入学习,作为一个非常受欢迎的人工智能方法,可以说是一个小区域在图像识别领域。它是一种机器学习,实际上来源于人工神经网络,是一个学习样本数据的特征方法。这是一个多层网络,可以学习的信息从底部到顶部的图像通过多层网络,以便提取样本的特征,然后进行识别和分类。深度学习的目的是让机器有同样的分析和学习能力作为人类的大脑。深入学习数据处理的能力(包括图片)是其他方法无法比拟的,和近年来取得的成就留下其他方法。本文全面综述了应用程序的研究进展深卷积神经网络在中国古代模式恢复,主要侧重于研究基于卷积神经网络。主要任务如下:(1)详细全面的介绍了卷积神经深处的基本知识和相关的摘要算法在文本预处理的三个方向,提供学习和神经网络。本文主要关注传统模式的相关机制修复基于深卷积神经网络,分析了关键的结构和原理。(2)研究基于深度图像恢复模型卷积网络和敌对的神经网络。模型主要由四个部分组成,即信息屏蔽,特征提取,生成网络,判别网络。 The main functions of each part are independent and interdependent. (3) The method based on the deep convolutional neural network and the other two methods are tested on the same part of the Qinghai traditional embroidery image data set. From the final evaluation index of the experiment, the method in this paper has better evaluation index than the traditional image restoration method based on samples and the image restoration method based on deep learning. In addition, from the actual image restoration effect, the method in this paper has a better image restoration effect than the other two methods, and the restoration results produced are more in line with the habit of human observation with the naked eye. SN - 1687-5265 UR - https://doi.org/10.1155/2021/2691346 DO - 10.1155/2021/2691346 JF - Computational Intelligence and Neuroscience PB - Hindawi KW - ER -