摘要
针对不同纹理的文本图像经Haar小波变换所产生的小波系数 ,利用非参数假设检验中的直方图及正态概率纸的方法统计其分布规律 ,并利用黄金分割找出分界点 ,从而得出结论 :不同纹理小波变换系数在各个区间上基本服从正态分布 .
On the basis of the wavelet coefficients by Haar wavelet transformation in different texture of document image, we make use of the normal probability-paper method in nonparametric hypothesis test to find their distribution rule. Then we study the distribution of the wavelet coefficients in each interval by the golden section. On the above rule, we come to the conclusion that the coefficients in each interval obey indeed normal distribution.
出处
《河南大学学报（自然科学版）》
CAS
2002年第2期28-31,共4页
Journal of Henan University:Natural Science
基金
河南省教委自然科学基金项目 (199912 0 0 0 3)
关键词
正态分布
拟合检验
黄金分割
正态概率纸
非参数假设检验
HAAR小波变换
normal distribution
simulation verification
golden section
normal probability paper
nonparametric hypothesis test
Haar wavelet transformation
