基于SIFT彩色描述子的彩色图像质量评价  

作　　者：陈伟静[1] 张轩[1] 徐仰彬[1] 

机构地区：[1]西安建筑科技大学理学院,陕西西安710055

出　　处：《电子制作》2013年第16期36-38,共3页Practical Electronics

摘　　要：图像处理系统性能优劣的评判往往需要一个合理迅速的图像质量评价算法作为支撑.传统的图像质量评价算法由于没有充分考虑人眼的视觉特性,使得质量评价结果与实际图像的人眼感知质量不符.本文通过分析图像中稳定极值点对人眼视觉的影响,提出一种新的基于SIFT彩色描述子的算法(WSEPSIM)来评价彩色图像,首先基于SIFT的彩色描述子WSIFT得到彩色图像的极值点,通过对比原图像及降质图像的极值点的变化规律得到WSEPSIM。实验结果表明,WSEPSIM的评价性能优于目前主流的图像质量评价标准PSNR和SSIM,是一种有效的彩色图像质量评价方法。Measurement of visual quality is of fundamental importance to some image processing applications,so an efficient image quality assessment algorithm is greatly needed.And the evaluation results of the conventional algorithms do not match to the ones of human vision because those algorithms ignore the characteristic of the Human Visual System(HVS).According to analysis of the image stability extreme point for the human eye visual impact, this paper propose a novel algorithm for color image quality assessment based on SIFT color descriptor.First based on SIFT color descriptor WSIFT to get extreme points,by comparing the change rule of extreme point between the original image and lower quality of the image we get the WSEPSIM,The experimental results show that the WSEPSIM evaluation performance is superior to the current mainstream of PSNR and SSIM image quality assessment standards, It is a kind of effective color image quality evaluation method.

关 键 词：图像质量评价 局部特征点 相似度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]