基于Contourlet变换和多尺度Rentinex的水下图像增强算法

石丹; 李庆武; 范新南; 霍冠英

doi:doi:10.3788/lop47.041001

激光与光电子学进展, 2010, 47 (4): 041001, 网络出版: 2010-03-29

基于Contourlet变换和多尺度Rentinex的水下图像增强算法下载： 745次

Underwater Image Enhancement Algorithm Based on Contourlet Transform and Multi-Scale Retinex

论文大纲

石丹 ^*李庆武范新南霍冠英

作者单位

河海大学计算机及信息工程学院,江苏常州 213022

摘要

针对水下图像对比度低、边缘模糊、噪声大等特点，提出一种基于非下采样Contourlet变换和多尺度Retinex的水下图像增强算法。将水下图像进行多尺度多方向的非下采样Contourlet变换;利用多尺度Retinex算法调整低频系数，提高图像整体对比度;在各带通方向子带上估计噪声，抑制模值小于阈值的系数，改进神经网络中的Sigmoid函数用于调节模值大于阈值的系数;经非下采样Contourlet逆变换得到增强图像。与几种传统增强算法相比，本算法处理的图像达到了抑制噪声、改善图像对比度、突出目标轮廓的目的，具有较高的对比度评估值。

Abstract

Considering the low contrast,fuzzy edge and strong noise of underwater images,an underwater image enhancement algorithm based on nonsubsampled Contourlet transform (NSCT) and multi-scale retinex is proposed. The underwater image is decomposed by nonsubsampled Contourlet transform. Then multi-scale Retinex (MSR) is used to enhance the image’s global contrast in the low frequency subband,and an improved Sigmoid function is used to process the coefficients at each scale in the directional bandpass subbands respectively,which suppresses small coefficients and enhances large coefficients by threshold denoising method. Finally,the enhanced coefficients are reconstructed to obtain enhanced image. Compared with the other traditional methods,the approach reduces the noise of original images,improves the contrast of the image,enhances object’s contour and achieves higher quantitative contrast assessment indicator.

参考文献

[1] . Land. The Retinex theory of color vision[J]. Sci. Am., 1977, 237(6): 108-128.

[2] T. J. Brown. An adaptive strategy for wavelet based image enhancement[C]. Proceedings of Irish Machine Vision and Image Processing Conference,2000. 67-81

[3] M. N. Donoho,M. Vetterli. Contourlets:A directional multiresolution image representation [C].Rochester:Proc.of IEEE ICIP,2002. 357-360

[4] M. N. Donoho,M. Vetterli. Contourlets,Beyond Wavelets[M]. New York:Academic Press,2002. 1-23

[5] . da Cunha,Jianping Zhou. The nonsubsampled contourlet transform:theory,design,and applications[J]. IEEE Trans. Image Process., 2006, 15(10): 3089-3101.

[6] Baolong Guo,Qiang Zhang,Ye Hou. Region-based fusion of infrared and visible images using nonsubsampled contourlet transform [J]. Chin. Opt. Lett.,2008,10(6):338-341

[7] 张强,郭宝龙. 基于非采样Contourlet变换的遥感图像融合算法[J]. 光学学报,2008,28(1):74-80

Zhang Qiang,Guo Baolong. Remote sensing image fusion based on the nonsubsampled contourlet transform[J]. Acta Optica Sinica. 2008,28(1):74-80

[8] 梁栋,殷兵,于梅等. 基于非采样Contourlet变换的自适应阈值图像增强算法[J]. 电子学报,2008,36(3):527-530

Liang Dong,Yin Bing,Yu Mei et al.. Image enhancement based on the nonsubsampled contourlet transform and adaptive threshold [J]. Acta Electronica Sinica. 2008,36(3):527-530

[9] 周旋,周树道,黄峰等. 基于小波变换的图像增强新算法[J]. 计算机应用,2005,25(3):606-608

Zhou Xuan,Zhou Shudao,Huang Feng et al.. New algorithm of image enhancement based on wavelet transform[J]. Comput. Appl.,2005,25(3):606-608

[10] . L. Donoho,I. M. Johnstone. Ideal spatial adaptation via wavelet shrinkage[J]. Biometrika, 1994, 81(3): 425-455.

[11] 石丹,李庆武,倪雪等. 基于Contourlet变换的红外图像非线性增强算法[J]. 光学学报,2009,29(2):342-346

Shi Dan,Li Qingwu,Ni Xue et al.. Infrared image nonlinear enhancement algorithm based on contourlet transform[J]. Acta Optica Sinica,2009,29(2):342-346

石丹, 李庆武, 范新南, 霍冠英. 基于Contourlet变换和多尺度Rentinex的水下图像增强算法[J]. 激光与光电子学进展, 2010, 47(4): 041001. Shi Dan, Li Qingwu, Fan Xinnan, Huo Guanying. Underwater Image Enhancement Algorithm Based on Contourlet Transform and Multi-Scale Retinex[J]. Laser & Optoelectronics Progress, 2010, 47(4): 041001.

基于Contourlet变换和多尺度Rentinex的水下图像增强算法下载： 745次

关于本站 Cookie 的使用提示

全站搜索

基于Contourlet变换和多尺度Rentinex的水下图像增强算法 下载： 745次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于Contourlet变换和多尺度Rentinex的水下图像增强算法下载： 745次