基于均匀空间色差度量的彩色图像椒盐噪声滤波算法  

Salt and pepper noise filtering algorithm for color images based on color difference measurement in uniform space

作　　者：刘辉[1] 王文哲[1] 许圣雷 LIU Hui;WANG Wen-zhe;XU Sheng-lei(Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, Chin)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《传感器与微系统》2018年第6期146-149,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61263017);昆明理工大学教学改革项目(10968397)

摘　　要：研究基于均匀空间的彩色图像椒盐噪声滤除方法,针对传统中值滤波会引入其他色彩的缺点,提出了一种符合人眼对色彩识别能力的矢量排序方法。在Lab空间下,像素点之间的欧几里得距离与实际色差成正比,据此建立矢量排序,依据排序结果利用中值滤波方法进行去噪,并与HSV,VMF和BVDF算法等其他滤波方法进行了对比研究,实验结果表明:所提方法不但能够有效改善图像质量,而且能够更好地保护图像的色彩信息,较传统彩色图像去噪算法有较好的优越性。A method of color image salt and pepper noise filtering based on uniform space is proposed. To overcome the weakness of traditional median filtering may bring in other colors,a vector sorting method which is consistent with human＇s ability of color recognition is proposed. In the Lab space,the Euclidean distance between pixels points is proportional to the actual color difference,on which the vector sorting is established. According to sorting result,as criteria uses method of median filtering to remove the noise. The results are compared with other filtering methods such as HSV,VMF andBVDF. Experimental results show that the method can not only improve image quality,but can protect color information of image better,and it is better than the traditional denoising algorithm of color image.

关 键 词：矢量排序 彩色图像 均匀空间 椒盐噪声 中值滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]