理想置乱图像差分直方图分布模型的数学验证  

The mathematical validation on the distribution model of ideal scrambled image′s difference histogram

作　　者：王聪丽[1,2] 陈志斌[1] 丁娜娜 

机构地区：[1]军械工程学院军械技术研究所,河北石家庄050003 [2]武警石家庄士官学校,河北石家庄050003

出　　处：《电子技术应用》2015年第1期107-110,114,共5页Application of Electronic Technique

摘　　要：目前图像置乱度评价算法缺乏统一的标准和模型,某些模型的提出缺乏科学依据与严格证明,如理想置乱图像的差分直方图分布模型。在分析置乱图像差分直方图分布的基础上,利用ChiSquare假设检验和回归分析方法进行差分直方图分布函数的拟合检验和回归系数预测。实验结果证明,在理想置乱情况下,图像的差分直方图应符合线性分布,为理想置乱图像差分直方图分布模型的建立提供了理论基础。The main shortage of evaluation methods on image scrambling degree is the lack of criterions and models, and some models have been presented without scientific basis. For example, the linear distribution model of ideal scrambled image＇s difference histogram has been advanced in paper without justified. Based on the difference histogram of scrambled image, Pearson Chi-Square hypothesis test and regression analysis are used to test its distribution characteristics in this paper. Simulation results show that the distribution of difference histogram of ideal scrambled image should accord with the linear model. The validation in this paper can provide precise theoretical basis to establish the linear model of difference histogram of ideal scrambled image.

关 键 词：图像置乱 置乱度评价 差分直方图 假设检验 回归分析 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]