基于自适应参数双边滤波和小波变换的图像检索方法  

IMAGE RETRIEVAL METOD BASED ON ADAPTIVE PARAMETER BILATERAL FILTERING AND WAVELET TRANSFORM

作　　者：邓冠男[1] 贾永鑫 刘乙鑫 Deng Guannan;Jia Yongxin;Liu Yixin(School of Science,Northeast Electric Power University,Jilin 132012,Jilin,China)

机构地区：[1]东北电力大学理学院,吉林吉林132012

出　　处：《计算机应用与软件》2023年第1期205-209,240,共6页Computer Applications and Software

摘　　要：提出一种基于自适应参数双边滤波和小波变换的图像检索方法,先采用自适应双边滤波算法,对图像进行平滑处理的同时保留图像主体的轮廓信息;结合基于自动阈值的小波变换方法,利用非线性阈值函数处理分解后的小波系数,突出低频主体信息,实现图像增强;利用感兴趣区域提取方法提取增强图像的感兴趣区域,并将该图像用于图像检索。采用corel-5k图像库中的图像用于仿真实验,结果表明,该算法能取得较高的信噪比,在图像检索系统中有较强的实用性。This paper proposes an image retrieval method based on adaptive parameter bilateral filtering and wavelet transform. The method adopted the adaptive bilateral filtering algorithm to smooth the image and retain the contour information of the main body of the image. Combined with the wavelet transform method based on automatic threshold, the nonlinear wavelet function was used to process the decomposed wavelet coefficients, so as to highlight the low-frequency subject information, and realize image enhancement. It applied the region of interest enhancement method to extract the region of interest of the enhanced image, and the image was used for image retrieval. The images in the corel-5k image library were used in simulation experiments. The results show that the algorithm can achieve a higher signal-to-noise ratio and is more practical in image retrieval systems.

关 键 词：图像检索 图像增强 双边滤波 小波变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]