Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (7): 226-228.DOI: 10.3778/j.issn.1002-8331.2010.07.069

• 工程与应用 • Previous Articles     Next Articles

Remote sensing image retrieval algorithm based on aiNet model of Artificial Immune Network

GENG Li-chuan1,3,WU Yun-dong1,2   

  1. 1.Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China
    2.66240 Troops,Beijing,China
    3.College of Sciences,Jimei University,Xiamen,Fujian 361021,China
  • Received:2008-09-08 Revised:2008-11-19 Online:2010-03-01 Published:2010-03-01
  • Contact: GENG Li-chuan



  1. 1.信息工程大学 测绘学院,郑州 450052
    3.集美大学 理学院,福建 厦门 361021
  • 通讯作者: 耿利川

Abstract: Images distribute very uneven in the feature space,sometimes encircle several centers influencing by several factors.A novel remote sensing image retrieval method based on aiNet model of Artificial Immune System(AIS) is proposed to settle this multi-center problem.aiNet is used to learn and memorize the user feedback information,so to find multi-global optimum solutions efficiently and improve the recognition of customers’ semantic target for system.This network has the properties of reducing redundancy,diversity,learning and memorizing,since then the shortcoming of running into local optimum solution of traditional algorithm can be avoided.Experimental results show that this approach can recognize the user feedback information efficiently and improve the retrieval accuracy.

Key words: Artificial Immune System(AIS), remote sensing image retrieval, relevance feedback, aiNet

摘要: 受多方面因素的影响,图像在特征空间中的分布是非常不均匀的,往往围绕多个中心。为了解决多个特征中心的问题,提出了一种基于aiNet人工免疫网络的遥感图像检索算法。该算法根据免疫网络机理及相关反馈技术,利用aiNet人工免疫网络对用户的反馈信息进行学习记忆,能有效寻找多个最优解,提高了系统对用户语义的理解能力。由于该网络具有减少冗余、多样性、学习和记忆的特性,避免了传统算法容易陷入局部最优的缺点。实验结果表明,该算法能有效理解用户的反馈信息,提高了传统检索方法的准确性。

关键词: 人工免疫系统, 遥感图像检索, 相关反馈, aiNet网络

CLC Number: