基于剪切波域改進(jìn)Gamma校正的醫(yī)學(xué)圖像增強(qiáng)算法
發(fā)布時(shí)間:2019-04-24 11:48
【摘要】:為了解決醫(yī)學(xué)圖像在采集和傳輸過程中引入噪聲和干擾導(dǎo)致圖像質(zhì)量惡化從而嚴(yán)重影響醫(yī)學(xué)診斷的問題,提出一種基于剪切波(shearlet)域改進(jìn)Gamma校正的圖像增強(qiáng)方法。首先,通過剪切波變換,把圖像分解成高頻部分和低頻部分;其次,用改進(jìn)的Gamma校正處理剪切波分解后的低頻部分以調(diào)整圖像的整體對比度,采用改進(jìn)的自適應(yīng)閾值函數(shù)對高頻部分進(jìn)行去噪;最后,把剪切波反變換的重構(gòu)圖像進(jìn)行模糊對比增強(qiáng),以突出圖像的細(xì)節(jié)信息。實(shí)驗(yàn)結(jié)果表明,本文算法的峰值信噪比(PSNR)、結(jié)構(gòu)相似度(SSIM)和絕對均值差(MAE)優(yōu)于其他對比算法,尤其是PSNR的提升更加明顯。這些客觀指標(biāo)說明,本文算法不僅能有效地抑制噪聲,而且能明顯改善增強(qiáng)對比度。從主觀方面觀察,本文算法與其他算法相比,能獲得更好的視覺效果。
[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.
【作者單位】: 新疆大學(xué)信息科學(xué)與工程學(xué)院;上海交通大學(xué)圖像處理與模式識別研究所;新西蘭奧克蘭理工大學(xué)知識工程與發(fā)現(xiàn)研究所;
【基金】:教育部促進(jìn)與美大地區(qū)科研合作與高層次人才培養(yǎng)(20142029)資助項(xiàng)目
【分類號】:TP391.41
本文編號: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.
【作者單位】: 新疆大學(xué)信息科學(xué)與工程學(xué)院;上海交通大學(xué)圖像處理與模式識別研究所;新西蘭奧克蘭理工大學(xué)知識工程與發(fā)現(xiàn)研究所;
【基金】:教育部促進(jìn)與美大地區(qū)科研合作與高層次人才培養(yǎng)(20142029)資助項(xiàng)目
【分類號】:TP391.41
【相似文獻(xiàn)】
相關(guān)期刊論文 前2條
1 郭盼;李杰;;一種基于剪切波和Top-hat變換的星點(diǎn)粗提取算法[J];長春大學(xué)學(xué)報(bào);2014年08期
2 ;[J];;年期
相關(guān)碩士學(xué)位論文 前9條
1 張?jiān)埔?低劑量CT圖像的質(zhì)量改善算法研究[D];鄭州大學(xué);2015年
2 吳欣亮;基于剪切波變換的紋理分類研究[D];西南交通大學(xué);2015年
3 徐榮;基于剪切波變換的圖像處理技術(shù)的研究[D];武漢紡織大學(xué);2016年
4 柴昱洲;分?jǐn)?shù)階M帶小波及剪切波域的圖像融合算法研究[D];西安建筑科技大學(xué);2016年
5 孫晨;基于全變分和剪切波變換的圖像去噪方法研究[D];天津大學(xué);2015年
6 孫美玲;基于最大熵和剪切波變換域特性的圖像水印隱藏算法研究[D];西北大學(xué);2016年
7 李新;Z~2上一類剪切波的構(gòu)造[D];河南大學(xué);2016年
8 王治成;基于非下采樣剪切波和RI-LPQ的圖像檢索技術(shù)研究[D];合肥工業(yè)大學(xué);2014年
9 張紅;基于剪切波的圖像復(fù)原算法研究[D];鄭州大學(xué);2014年
,本文編號:2464419
本文鏈接:http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2464419.html
最近更新
教材專著