基于灰色关联分析的图像置乱程度评价方法  

Image scrambling degree evaluation method based on GRA

作　　者：马苗[1,2] 谭永杰[1] 何雪莉[1] 

机构地区：[1]陕西师范大学计算机科学学院,西安710062 [2]西北工业大学计算机学院,西安710072

出　　处：《计算机应用研究》2009年第4期1595-1597,共3页Application Research of Computers

基　　金：中国博士后科学基金资助项目(20060401009);陕西省自然科学基金资助项目(2007D07);国家教育部科学技术研究重点基金项目(107106);陕西师范大学研究生培养创新基金项目(2008CXS024)

摘　　要：为有效衡量图像置乱的程度,引入灰色理论中的灰色关联分析,提出一种新的置乱效果评价方法。该方法首先将置乱图像分块,通过计算各子块图像中每行元素的灰度均值来统计各子块的灰度信息,建立小样本序列;然后利用灰色关联分析理论计算各序列之间的灰度信息关联度来评判各子图像灰度信息的关联程度,从而获取图像的置乱效果。实验表明,该方法能有效地评价不同置乱变换的效果,且评判无须原图像参与,与基于SNR的置乱评判方法相比,能更加客观地评判置乱效果,且与人眼目测结果相符。In order to evaluate the image scrambling degree effectively, introducing the grey relation analysis theory, and then suggested a new method of image scrambling. The method firstly divided the scrambled image into several blocks, then compu- ted the average of every line pixel values in the sub-images to static the gray information sequence of each blocks, and made these sequences be small samples sequences. Finally calculated the gray relevancy of every two sequences using gray relation analysis to evaluate the image scrambling degree. Experimental results show that the method can efficiently evaluate the scram- bling effect of different scrambling transformation, running without the origin image involved. Compared with SNR, it can eva- luate the scrambling effect more objectively and be consistent with the perception of human visual system.

关 键 词：图像置乱 置乱程度 灰色关联分析 信噪比 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN941.5[自动化与计算机技术—计算机科学与技术]