一种基于修改特征权重的图像检索反馈算法的研究与实现

Research and Realization of An Image Retrieval Feedback Algorithm Based on Feature Weighting Modification

图像检索系统是根据用户指定的信息自适应地调整查询策略,实现智能地从图像数据库中查找出特定图像的系统。文章提出一种新的基于修改特征权重的相关反馈算法,增加未标注图像与反例图像训练样本数,解决相关反馈算法中忽略未被标注的图像的问题。实验证明,采用该算法的系统比传统的检索系统有优势,精度更高。

Image retrieval system refers to the technology of retrieving particular images from image data base automatically and intelligently by adjusting searching strategy according to the information offered by the user. This paper introduces a new algorithm of relevance feedback based on feature weighting modification, and increases the training sample number with un - labeled image and counter - example image, solving the prob- lems of neglecting un - labeled image. Experiments show that the new system results in higher precision and thus gain an advantage over the traditional ones.