带权重分数阶积分图像去噪方法  

Image Denoising Method for Weighted Fractional Integral

作　　者：娄联堂[1] 方自成 韦茜妤 吴高林[1] 

机构地区：[1]中南民族大学数学与统计学学院,武汉430074

出　　处：《中南民族大学学报（自然科学版）》2016年第3期146-150,共5页Journal of South-Central University for Nationalities：Natural Science Edition

基　　金：国家自然科学基金资助项目(60975011);中南民族大学中央高校基本科研业务费专项资金资助项目(CZW15051;YZZ13003)

摘　　要：为了在图像去噪的同时保留更多图像的细节信息,在Riemann-Liouville定义的分数阶积分基础上,在数字信号的近似过程中引入权重参数,提出了一种通过调节权重与积分阶次并结合8个方向上的掩膜进行图像去噪的方法.实验结果表明:与传统去噪方法相比较,该方法不仅可以提高图像的峰值信噪比,而且还可以更好地保留图像纹理细节信息.In order to preserve more details of the image while image denoiseing, based on the fractional-order integral definition of Riemann-Liouville, this paper introduced weight parameters for the approximation process of digital signal, and proposed a method of the masks on eight directions by adjusting the value of weight and integral order. The experimental results show that compared with the traditional denoising methods, the proposed method not only can improve the peak signal-to-noise ratio of the image, but also can retain the image detailed texture better.

关 键 词：权重 分数阶积分 图像去噪 峰值信噪比 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]