一种基于小波域的图像增强方法  

An image enhancement method based on wavelet domain

作　　者：阿依尼沙汗·买吐孙 伊克沙尼·伊力哈木 吐尔洪江·阿布都克力木[1] Ayinishahan Maitusun;Yikeshani Yilihamu;Turghunjan Abdukirim(College of Mathematical Sciences,Xinjiang Normal University,Urumqi 830017,China)

机构地区：[1]新疆师范大学数学科学学院,新疆乌鲁木齐830017

出　　处：《电子设计工程》2021年第24期24-27,33,共5页Electronic Design Engineering

基　　金：国家自然科学基金资助项目(11261061,61362039,10661010);新疆维吾尔自治区自然科学基金资助项目(200721104);新疆师范大学数学教学资源开发重点实验室招标课题(XJNUSY082017B03)。

摘　　要：图像增强方法通常会放大原图像中噪声的分量,针对这一问题,提出了一种基于小波变换的图像增强方法。该方法将小波多尺度积法的特性和分段非线性变换法的特性相结合,克服了对图像进行单一的传统图像增强方法时会丢失图像细节信息、增强图像噪声等的不足。利用小波变换中各尺度上小波系数间的相关性特点对高频部分进行系数相关运算,对低频部分采用分段非线性增强处理,将处理后的低频分量和各个高频分量进行小波逆变换重构。实验结果表明,该方法有效地抑制了噪声,处理后的图像明暗较为清楚,有利于进一步进行分析和处理。Image enhancement methods usually amplify the noise component in the original image.To solve this problem,an image enhancement method based on wavelet transform is proposed.This method combines the characteristics of wavelet multi⁃scale product method with the characteristics of piecewise nonlinear transformation method,and overcomes the shortcomings of single traditional image enhancement method,such as losing image detail information and enhancing image noise.Using the correlation between wavelet coefficients at various scales in wavelet transform,the high⁃frequency part is correlated,and the low⁃frequency part is enhanced by subsection nonlinearity,and the processed low⁃frequency component and each high⁃frequency component are reconstructed by inverse wavelet transform.The experimental results show that this method can effectively suppress the noise,and the processed image is bright and dark,which is beneficial to further analysis and processing.

关 键 词：小波变换 小波多尺度积 分段非线性变换 图像增强 

分 类 号：TN29[电子电信—物理电子学]