正交Gaussian-Krawtchouk不变矩的构建及在图像匹配中的应用研究  

CONSTRUCTION OF INVARIANTS OF ORTHOGONAL GAUSSIAN-KRAWTCHOUK MOMENT AND THE APPLICATION IMAGE MATCHING

作　　者：刘欢[1,2] 肖根福 熊勇[3] LIU Huan;XIAO Gen-fu;XIONG Yong(School of Electronic and Information Engineering,Jinggangshan University,Ji’an,Jiangxi 343009,China;Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth,Ji’an,Jiangxi 343009,China;School of Electromechanical,Ji’an,Jiangxi 343009,China)

机构地区：[1]井冈山大学电子与信息工程学院,江西吉安343009 [2]江西省农作物生长物联网技术工程实验室,江西吉安343009 [3]井冈山大学机电学院,江西吉安343009

出　　处：《井冈山大学学报（自然科学版）》2021年第2期61-69,75,共10页Journal of Jinggangshan University (Natural Science)

基　　金：国家自然科学基金项目(61640412,61762052,42061055);江西省自然科学基金项目(20192BAB207021,20202BABL202047);江西省教育厅科技计划项目(GJJ201008);江西省高校人文社科项目(YS20129)。

摘　　要：针对基于几何矩及不变矩的图像特征描述存在信息冗余,计算复杂,图像表征能力不强等问题,本文深入研究了正交的Gaussian-Krawtchouk矩及其不变矩的表达形式。依据不同的尺度因子特点,提出了基于多尺度Gaussian-Krawtchouk不变矩的图像局部特征描述方法,并用于五种不同类型图像的特征匹配。实验结果表明,这种不变矩较其他传统的特征描述方法具有更好的图像表征能力,更强的数字稳健性。该不变矩用于图像匹配是有效可行的,具有良好的实用价值。Aiming at the problem of information redundancy,complex calculation and low image representation of the method of the image feature description based on the geometric moment and invariant moment,orthogonal Gaussian-Krawtchouk moment and its invariant moment are deeply studied.According to the traits of different scale parameters,a description method on image local features based on multi-scale Gaussian-Krawtchouk invariant moment is presented,and was applied in the tests of image trait matching in five different types of images.The experimental results show that the proposed description method performs much better than the other traditional description methods with better image representation ability and stronger digital stability.The invariant moment applied in image matching is feasible and validate.It can offer a nice reference value.

关 键 词：正交Gaussian-Krawtchouk矩 不变矩 GKM描述子 图像局部特征描述 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]