基于小波域分析的图像模糊度算法研究  

A Novel Measure of Image Blur Based on Perception

作　　者：张旗[1] 梁德群[2] 樊鑫[3] 

机构地区：[1]大连海事大学自动化与电气工程学院,大连116026 [2]大连海事大学信息工程学院,大连116026 [3]西安交通大学图像处理与模式识别研究所,西安710049

出　　处：《计算机工程》2004年第17期136-137,192,共3页Computer Engineering

摘　　要：针对模糊图像处理问题,提出了一种基于小波域分析的测量图像模糊程度的算法。这种算法可在图像处理中获得该图像的模糊程度(图像模糊度)的客观、准确的度量。实验结果表明:该模糊度与人的主观排序相吻合,可用于图像品质的评价。A fast algorithm for determining image blur degree (IBD) according to this definition is presented. First, based on the distribution of wavelet high-frequency coefficients,the smooth regions and edge regions in an image are extracted . In the second part of the algorithm, these regions are weighted and the IBD of the image is worked out. The performance of the method is demonstrated on some images, and the measure has good correlation with subjective ranking and can be used to assess image quality more reasonably.

关 键 词：小波变换 图像模糊度 边缘活动度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]