计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (7): 15-30.DOI: 10.3778/j.issn.1002-8331.2205-0503

• 热点与综述 • 上一篇    下一篇

图神经网络及其在图像处理领域的研究进展

蒋玉英,陈心雨,李广明,王飞,葛宏义   

  1. 1.河南工业大学 粮食信息处理与控制教育部重点实验室,郑州 450001
    2.河南工业大学 人工智能与大数据学院,郑州 450001
    3.河南省粮食光电检测与控制重点实验室,郑州 450001
    4.河南工业大学 信息科学与工程学院,郑州450001
  • 出版日期:2023-04-01 发布日期:2023-04-01

Graph Neural Network and Its Research Progress in Field of Image Processing

JIANG Yuying, CHEN Xinyu, LI Guangming, WANG Fei, GE Hongyi   

  1. 1.Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education, Zhengzhou 450001, China
    2.School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, China
    3.Henan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou 450001, China
    4.School of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China
  • Online:2023-04-01 Published:2023-04-01

摘要: 图神经网络(graph neural network,GNN)是一种基于深度学习的图结构数据处理模型,因良好的可解释性和对图结构数据强大的非线性拟合能力而受到研究者广泛关注。随着GNN的逐步优化,GNN与图像处理技术实现融合发展,在图像分类、人体解析和视觉问答等方面取得重大突破。对图像处理技术和传统神经网络理论进行介绍,并对五类GNN的原理、特点和不足进行分析与总结;同时从数据集和性能评估指标两个角度对文中所述的常用模型进行对比与总结,并补充介绍了九种常见的图像处理领域公共数据集;最后深入分析了GNN在图像处理领域中有待改进的方面,并对其应用前景进行展望。

关键词: 图神经网络(GNN), 深度学习, 图结构, 图像处理

Abstract: Graph neural network (GNN) is a deep learning-based model for processing graph-structured data, which has received much attention from researchers for its good interpretability and powerful nonlinear fitting ability to graph-structured data. With the rise of GNN, GNN has been developed to integrate with image processing techniques and has made breakthroughs in image classification, human body analysis and visual quizzing. Firstly, image processing techniques and the theory of traditional neural networks are introduced, and the principles, characteristics and shortcomings of five major classes of GNNs are analyzed. Secondly, the applications of GNN in the image processing field from five technical levels are analyzed respectively, and the representative models of each class of methods are listed. Thirdly, the common models described in the paper are compared and summarized from the perspective of both datasets and performance evaluation metrics, and nine common public datasets in image processing are introduced in addition. Finally, areas for improvement in GNN in the field of image processingare analyzed in depth, and the prospects of its application in the field of image processing are presented.

Key words: graph neural network (GNN),  , deep learning,  , graph structure,  , image processing