计算机科学与探索 ›› 2011, Vol. 5 ›› Issue (1): 32-37.DOI: 10.3778/j.issn.1673-9418.2011.01.003

• 学术研究 • 上一篇    下一篇

利用蚁群算法的记忆式图像检索方法

陈光鹏+, 杨育彬   

  1. 南京大学 软件新技术国家重点实验室, 南京 210093
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-01-01 发布日期:2011-01-01
  • 通讯作者: 陈光鹏

Memory-type Image Retrieval Method Based on Ant Colony Algorithm

CHEN Guangpeng+, YANG Yubin   

  1. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-01-01 Published:2011-01-01
  • Contact: CHEN Guangpeng

摘要: 如何有效利用用户的相关反馈信息来进行基于语义的图像检索, 是一个具有重要意义并且极具挑战性的问题。介绍了一种基于蚁群算法的记忆式图像检索方法, 它是传统记忆式图像检索方法的一种改进。用蚁群算法的思想, 利用用户的反馈信息建立图像的语义网络, 并依据该语义网络用迭代的方法来检索图像。实验表明, 该方法不仅有效, 而且存储量小、计算量少。

关键词: 图像检索, 相关反馈, 蚁群算法, 记忆式学习, 长期学习, 语义网络

Abstract: It is a significant and challenging issue to utilize relevant feedback of users effectively to implement the semantic-based image retrieval. This paper introduces a memory learning based image retrieval method by using the ant colony algorithm. It establishes a semantic network of images according to users’ relevant feedback based on the ant colony algorithm, and then retrieves images by using the semantic network iteratively. Experiment results show that this approach is effective and with less need of storage and computing.

Key words: image retrieval, relevant feedback, ant colony algorithm, memory learning, long-term learning, semantic network

中图分类号: