基于快速小波变换的高适应性图像检索技术研究  

Highly Adaptive Image Retrieval Technology Based on Fast Wavelet Transform

作　　者：刘晙[1] 茹庆云[1] 

机构地区：[1]河南机电高等专科学校计算机科学与技术系,河南新乡453000

出　　处：《图学学报》2014年第2期262-267,共6页Journal of Graphics

基　　金：河南省基础与前沿技术研究计划基金资助项目(082300410390);河南省高等学校教学工程项目--教学团队(豫教高2012[1099]号);精品资源共享课程(豫教高2012[1185]号)

摘　　要：在目前已有的研究工作中,基于自适应小波的图像特征在基于内容的图像检索领域获得了广泛的应用。但这些方法存在一个共同问题,即采用相同的小波基描述不同的查询图像。为了提高图像检索技术的自适应能力,本文对不同的查询图像设计不同的小波基表示,从而实现用可调整的距离测度表征不同类别图像的特征改变。为了进一步降低表征图和表征导数图的求取时间,该文使用了近似泰勒展开。实验结果表明,这种新的图像检索技术具有高度的自适应能力,检索性能也大幅度提高。In the existing research in the field of content-based image retrieval, image features obtained by adaptive wavelet transform have a wide range of applications. There is a common problem in these methods that different query images are described with the same wavelet basis. In order to improve the adaptive capacity of image retrieval techniques, different wavelet bases are designed for different query images. Different wavelet bases can be used in adjusting retrieval performance for different query images, and the extraction time does not significantly increase. The experimental results show that this new image retrieval technology has a high adaptive capacity and its retrieval performance is also greatly improved.

关 键 词：图像检索 小波变换 小波基 自适应 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]