基于改进脊波变换的红外视频图像高质量复原  

High quality infrared video image restoration algorithm based on the improved ridgelet transform

作　　者：郎川萍[1] 杨仁怀[1] 

机构地区：[1]四川交通职业技术学院计算机工程系,成都611130

出　　处：《激光技术》2015年第2期247-251,共5页Laser Technology

摘　　要：为了实现红外视频降质图像高质量复原,采用一种基于改进脊波变换的图像复原算法来进行处理。该算法首先对降质图像进行改进脊波变换,然后提出一种具有加权改进自适应伪中值滤波算法对脊波系数进行处理,最后针对滤波后图像中时常出现的"环绕"现象,引入自适应Wiener滤波算法来抑制。进行了理论分析和实验验证,取得了相关模拟降质图像、真实降质图像以及峰值信噪比的测试数据。结果表明,该算法性能优于伪中值滤波以及两类脊波变换去噪算法。这对于实现红外视频降质图像复原研究是有帮助的。In order to reconstruct high quality infrared video images from the degraded images,an image restoration algorithm was adopted based on the improved ridge wavelet transform. Firstly,the ridge wavelet transform was carried out for the degraded images. Then,one weighted improved adaptive pseudo median filtering algorithm was used to process the ridge wave coefficients. Finally,adaptive Wiener filtering algorithm was introduced to suppress for＂wrap around＂effect of images after filtering. After theoretical analysis and experimental verification,the relevant simulated degraded images,the real degraded images and the peak signal to noise ratio were obtained. The results show that the algorithm in this paper is superior to the algorithms,such as the pseudo median filtering and two types of ridge wavelet transform denoising algorithms. The study is helpful for the research of infrared video degraded image restoration.

关 键 词：图像处理 图像复原 红外视频图像 小波变换 脊波变换 伪中值滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]