基于剪切波域改进Gamma校正的医学图像增强算法
发布时间：2019-04-24 11:48
【摘要】：为了解决医学图像在采集和传输过程中引入噪声和干扰导致图像质量恶化从而严重影响医学诊断的问题,提出一种基于剪切波(shearlet)域改进Gamma校正的图像增强方法。首先,通过剪切波变换,把图像分解成高频部分和低频部分;其次,用改进的Gamma校正处理剪切波分解后的低频部分以调整图像的整体对比度,采用改进的自适应阈值函数对高频部分进行去噪;最后,把剪切波反变换的重构图像进行模糊对比增强,以突出图像的细节信息。实验结果表明,本文算法的峰值信噪比(PSNR)、结构相似度(SSIM)和绝对均值差(MAE)优于其他对比算法,尤其是PSNR的提升更加明显。这些客观指标说明,本文算法不仅能有效地抑制噪声,而且能明显改善增强对比度。从主观方面观察,本文算法与其他算法相比,能获得更好的视觉效果。
[Abstract]:In order to solve the problem of image quality deterioration caused by noise and interference in the process of medical image acquisition and transmission, an image enhancement method based on shear wave (shearlet) domain improved Gamma correction is proposed. Firstly, the image is decomposed into high-frequency part and low-frequency part by shear wave transform. Secondly, the improved Gamma correction is used to deal with the low frequency part after the shear wave is decomposed to adjust the whole contrast of the image, and the improved adaptive threshold function is used to Denoise the high frequency part. Finally, the reconstructed image of shear wave inverse transform is enhanced by fuzzy contrast to highlight the details of the image. Experimental results show that the peak signal to noise ratio (PSNR) of (PSNR), structure similarity (SSIM) and absolute mean difference (MAE) are better than other contrast algorithms, especially the enhancement of PSNR is more obvious. These objective indexes show that the proposed algorithm can not only suppress the noise effectively, but also improve the contrast obviously. From the subjective point of view, compared with other algorithms, the proposed algorithm can achieve better visual effect.
【作者单位】： 新疆大学信息科学与工程学院;上海交通大学图像处理与模式识别研究所;新西兰奥克兰理工大学知识工程与发现研究所;
【基金】：教育部促进与美大地区科研合作与高层次人才培养(20142029)资助项目
【分类号】：TP391.41
本文编号：2464419
[Abstract]:In order to solve the problem of image quality deterioration caused by noise and interference in the process of medical image acquisition and transmission, an image enhancement method based on shear wave (shearlet) domain improved Gamma correction is proposed. Firstly, the image is decomposed into high-frequency part and low-frequency part by shear wave transform. Secondly, the improved Gamma correction is used to deal with the low frequency part after the shear wave is decomposed to adjust the whole contrast of the image, and the improved adaptive threshold function is used to Denoise the high frequency part. Finally, the reconstructed image of shear wave inverse transform is enhanced by fuzzy contrast to highlight the details of the image. Experimental results show that the peak signal to noise ratio (PSNR) of (PSNR), structure similarity (SSIM) and absolute mean difference (MAE) are better than other contrast algorithms, especially the enhancement of PSNR is more obvious. These objective indexes show that the proposed algorithm can not only suppress the noise effectively, but also improve the contrast obviously. From the subjective point of view, compared with other algorithms, the proposed algorithm can achieve better visual effect.
【作者单位】： 新疆大学信息科学与工程学院;上海交通大学图像处理与模式识别研究所;新西兰奥克兰理工大学知识工程与发现研究所;
【基金】：教育部促进与美大地区科研合作与高层次人才培养(20142029)资助项目
【分类号】：TP391.41
【相似文献】
相关期刊论文 前2条
1 郭盼;李杰;;一种基于剪切波和Top-hat变换的星点粗提取算法[J];长春大学学报;2014年08期
2 ;[J];;年期
相关硕士学位论文 前9条
1 张云逸;低剂量CT图像的质量改善算法研究[D];郑州大学;2015年
2 吴欣亮;基于剪切波变换的纹理分类研究[D];西南交通大学;2015年
3 徐荣;基于剪切波变换的图像处理技术的研究[D];武汉纺织大学;2016年
4 柴昱洲;分数阶M带小波及剪切波域的图像融合算法研究[D];西安建筑科技大学;2016年
5 孙晨;基于全变分和剪切波变换的图像去噪方法研究[D];天津大学;2015年
6 孙美玲;基于最大熵和剪切波变换域特性的图像水印隐藏算法研究[D];西北大学;2016年
7 李新;Z~2上一类剪切波的构造[D];河南大学;2016年
8 王治成;基于非下采样剪切波和RI-LPQ的图像检索技术研究[D];合肥工业大学;2014年
9 张红;基于剪切波的图像复原算法研究[D];郑州大学;2014年
，本文编号：2464419
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2464419.html
