计算机应用 ›› 2018, Vol. 38 ›› Issue (12): 3399-3402.DOI: 10.11772/j.issn.1001-9081.2018051041

• 人工智能 • 上一篇    下一篇

基于复杂网络描述的图像深度卷积分类方法

洪睿, 康晓东, 郭军, 李博, 王亚鸽, 张秀芳   

  1. 天津医科大学 医学影像学院, 天津 300203
  • 收稿日期:2018-05-21 修回日期:2018-07-06 出版日期:2018-12-10 发布日期:2018-12-15
  • 通讯作者: 康晓东
  • 作者简介:洪睿(1993-),男,内蒙古通辽人,硕士研究生,主要研究方向:图像处理;康晓东(1964-),天津人,教授,博士,CCF高级会员,主要研究方向:医学图像处理、医疗信息系统集成;郭军(1972-),男,四川成都人,实验师,主要研究方向:实验技术;李博(1987-),男,天津人,硕士研究生,主要研究方向:医疗信息系统集成;王亚鸽(1992-),女,河南平顶山人,硕士研究生,主要研究方向:医学图像处理;张秀芳(1995-),女,安徽宣城人,主要研究方向:医学图像处理。
  • 基金资助:
    天津市重点基金资助项目(17JC20J32500)。

Image deep convolution classification method based on complex network description

HONG Rui, KANG Xiaodong, GUO Jun, LI Bo, WANG Yage, ZHANG Xiufang   

  1. School of Medical Image, Tianjin Medical University, Tianjin 300203 China
  • Received:2018-05-21 Revised:2018-07-06 Online:2018-12-10 Published:2018-12-15
  • Contact: 康晓东
  • Supported by:
    This work is partially supported by the Key Foundation of Tianjin (17JC20J32500).

摘要: 为了在不增加较多计算量的前提下,提高卷积网络模型用于图像分类的正确率,提出了一种基于复杂网络模型描述的图像深度卷积分类方法。首先,对图像进行复杂网络描述,得到不同阈值下的复杂网络模型度矩阵;然后,在图像度矩阵描述的基础上,通过深度卷积网络得到特征向量;最后,根据得到的特征向量进行K近邻(KNN)分类。在ILSVRC2014数据库上进行了验证实验,实验结果表明,所提出的模型具有较高的正确率和较少的迭代次数。

关键词: 复杂网络, 深度卷积神经网络, AlexNet, 度矩阵, 图像分类

Abstract: In order to improve the accuracy of image classification with convolution network model without increasing more computation, a new image deep convolution classification method based on complex network description was proposed. Firstly, the complex network model degree matrices under different thresholds were obtained by using complex network description of image. Then, the feature vector was obtained by deep convolution neural networks based on degree matrix description of image. Finally, the obtained feature vectors were used for image K-Nearest Neighbors (KNN) classification. The verification experiments were carried out on the ImageNet Large Scale Visual Recognition Challenge 2014 (ILSVRC2014) database. The experimental results show that the proposed model has higher accuracy and fewer iterations.

Key words: complex network, Deep Convolution Neural Network (DCNN), AlexNet, degree matrix, image classification

中图分类号: