小波变换和直方图均衡化的保持色调不变彩色图像增强算法  被引量:14

Color image enhancement algorithm based on wavelet transform and histogram equal ization

在线阅读下载全文

作  者:阿卜杜如苏力·奥斯曼[1] 艾力米努·阿布力江 Abudurusuli Aosiman;Ailiminuer Abulijiang(College of Mathematical Sciences,Xinjiang Normal University,Xinjiang,Urumqi 830017;School of mathematics and Physics,Xinjiang Teachers College,Xinjiang,Urumqi 830043)

机构地区:[1]新疆师范大学数学科学学院,新疆乌鲁木齐830017 [2]新疆师范高等专科学校数理学院,新疆乌鲁木齐830043

出  处:《光电子.激光》2021年第1期14-18,共5页Journal of Optoelectronics·Laser

基  金:自治区高校科研计划自然科学青年项目;新疆师范大学数学教学资源开发实验室招标课题(XJNUSYS082017B07);新疆师范高等专科学校院级课题(XJJY201709)资助项目。

摘  要:彩色图像增强的目的是保持色调的前提下加强图 像对比度,提高彩色图像视觉效果,文中提出小波变换域内色调不变 彩色图像增强算法,RGB彩色空间中,对各通道进行小波分解,高频部分进行非线性变换, 突出细节信息,然后通过小波逆 变换重构图像,然后对图像进行限制对比度直方图均衡化后与原图比较算出增强因子,最后 处理gamut问题,得到保持色调 不变的增强图像,在相同条件下与其它彩色图像增强算法进行性能比较,实验结果表明,该 算法对质量不同的彩色图像有较 好的增强效果,增强了图像细节和对比度,并具有自适应能力。The purpose of color image enhancement is to enhance the image contras t and improve the visual effect of color image on the premise of maintaining the hue.In this paper,a color image′ enhancement alg orithm based on wavelet transform is proposed.In RGB color space,each channel is decomposed by wavelet transform,and the high frequ ency compenent is enhanced by nonlinear function to highlight the details.and the image is reconstructed by inverse wavelet transfor m,Then,the enhancement factor is calculated by comparing the image with the original image after histogram equalization,and th e gamut problem is processed to obtain the hue preserving enhanced image.The performance of the algorithm is compared with oth er color image enhancement algorithms under the same conditions.Experimental results show that the algorithm has good enhanceme nt effect on color images with different quality, enhances image details and contrast,and has adaptive ability.

关 键 词:直方图均衡化 保持色调 彩色图像增强 小波变换 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象