Image classification method and system based on graph convolutional neural network

The invention provides an image classification method and system based on a graph convolutional neural network. The method specifically comprises the following steps: crawling a segment of text information corresponding to an image on a network by using a crawler according to an image label; preprocessing the text information to obtain words; calculating PMI values between the words and TF-IDF values between the images and the words; forming a graph according to the PMI value and the TF-IDF, and forming graph structure data taking the image and words as nodes; processing the graph structure data by using a graph convolutional neural network to obtain an image classification result; the method has the beneficial effects that corresponding text description information is added to each imageon the basis of original image data, and the image classification accuracy is improved by utilizing the image convolutional neural network. 本发明提供一种基于图卷积神经网络的图像分类方法及系统，具体包括：用爬虫根据图像标签在网络上爬取图像对应一段文本信息；对所述文本信息预处理，得到词语；计算词语与词语之间的P