张书波,钟廷勇,贾宇明.能量制约耦合比值一致性约束的图像匹配算法[J].电子测量与仪器学报,2020,34(3):9-16
能量制约耦合比值一致性约束的图像匹配算法
Image matching algorithm based on energy constraints and ratio consistency constraints
  
DOI:
中文关键词:  图像匹配  Hessian矩阵  Hu不变矩  欧氏距离度量  能量制约  比值一致性约束
英文关键词:image matching  Hessian matrix  Hu invariant moment  Euclidean distance measure  energy constraints  ratio consistency constraints
基金项目:重庆市教委科学技术研究计划(KJQN201905404)、教育部人文社会科学重点研究基地重点项目(15JJD790044)资助
作者单位
张书波 1.重庆科创职业学院人工智能学院 
钟廷勇 2.重庆工商大学会计学院 
贾宇明 3.电子科技大学通信与信息工程学院 
AuthorInstitution
Zhang Shubo 1.College of Artificial Intelligence, Chongqing Creation Vocational College 
Zhong Tingyong 2.College of Accounting, Chongqing University of Industry and Commerce 
Jia Yuming 3.College of Communication and Information Engineering, University of Electronic Science and Technology of China 
摘要点击次数: 186
全文下载次数: 1972
中文摘要:
      针对当前较多图像匹配算法主要依靠阈值调节来完成特征匹配,导致算法的匹配正确度不高以及鲁棒性较差,设计了一种采用比值一致性约束的图像匹配算法。通过盒式滤波器替代高斯偏导函数,求取SIFT行列式,以提取图像特征。在特征点的邻域内计算Hu不变矩,求其特征向量。以特征点的向量为依据,并引入特征点邻域的区域能量,以获取特征匹配结果。利用匹配点对在空间上的距离关系,建立比值一致性约束方法,利用匹配点对的欧氏度量比值,搜索错误匹配,优化特征匹配结果。通过实验分析发现,与当前已有的图像匹配算法相比,所提算法的具有更高的匹配正确度和鲁棒性。
英文摘要:
      In view of the current many image matching algorithms that mainly rely on threshold adjustment to complete feature matching, resulting in low matching accuracy and poor robustness of the algorithm. In this paper, an image matching method using ratio consistency constraints is designed on the basis of matrix. The box filter is used to approximate the Gauss partial derivative function, and the determinant is obtained by convolution of the box filter and the image on the basis of the matrix. The image features are extracted by the determinant. Hu invariant moments are computed in the neighborhood of feature points and their eigenvectors are obtained. Based on the vectors of feature points, the region energy of the neighborhood of feature points is introduced to obtain the matching results. Using the distance relationship between matching points in space, the ratio consistency constraint method is established. The Euclidean metric ratio of matching points is used to search for wrong matching and optimize the result of feature matching. Through experimental analysis, it is found that the matching results of the proposed method have better matching accuracy and robustness than those of the current methods.
查看全文  查看/发表评论  下载PDF阅读器