Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (2): 511-516.DOI: 10.11772/j.issn.1001-9081.2020050747

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Feature matching method based on weighted similarity measurement

HU Lihua, ZUO Weijian, NIE Yaoyao   

  1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan Shanxi 030024, China
  • Received:2020-06-02 Revised:2020-08-21 Online:2021-02-10 Published:2020-09-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61873264).


胡立华, 左威健, 聂瑶瑶   

  1. 太原科技大学 计算机科学与技术学院, 太原 030024
  • 通讯作者: 胡立华
  • 作者简介:胡立华(1982-),女,山西忻州人,副教授,博士,CCF会员,主要研究方向:计算机视觉、人工智能、模式识别;左威健(1995-),男,山西大同人,硕士研究生,主要研究方向:特征匹配、三维重建;聂瑶瑶(1995-),女,山西运城人,硕士研究生,主要研究方向:计算机视觉、三维重建。
  • 基金资助:

Abstract: In order to solve the problems of poor robustness and high mismatch rate caused by the noise, illumination and scale in the image feature matching process, a feature matching method based on Weighted Similarity Measurement (WSM) was proposed. At first, FM_GMC (Feature Matching based on Grid and Multi-Density Clustering) algorithm was adopted to divide image into several feature clustering blocks. Secondly, in each feature clustering block, the edge feature points were attracted by Canny and descripted by Scale-Invariant Feature Transform (SIFT). Thirdly, the similarity measurements were performed on the Hausdorff distance of spatial context information between feature clustering blocks, the Euclidean distance between appearance descriptors of image feature points and Normalized Cross Correlation (NCC) by using weighting methods. Finally, the similarity measurement results were further optimized according to Nearest Neighbor Distance Ratio (NNDR), so as to determine the feature matching result. With the ancient architecture images as the dataset, the experimental results show that the WSM method has an average matching precision of 92%, and is superior to commonly matching algorithms on matching number and matching precision. Therefore, the effectiveness and robustness of WSM method are verified.

Key words: feature matching, similarity measurement, Scale Invariant Feature Transform (SIFT), Canny algorithm, ancient architecture image

摘要: 针对图像特征匹配过程中采集图像易受噪声、光照、尺度等因素影响使产生的匹配结果鲁棒性差、误匹配率高等问题,提出一种基于加权相似性度量(WSM)的特征匹配方法。该方法首先采用基于网格多密度聚类的特征匹配(FM_GMC)算法对原始图像进行特征聚类块划分;其次在每一特征聚类块中,采用Canny提取边缘特征点并使用尺度不变特征变换(SIFT) 进行描述;然后采用加权的方式对特征聚类块之间的空间上下文信息间的Hausdorff距离、图像特征点外观描述子间的欧氏距离以及图像特征点的局部几何灰度信息的归一化互相关度量(NCC)进行相似性度量;最后依据最近邻距离比值(NNDR)对相似性度量结果进一步优化,从而确定特征匹配结果。以古建筑图像为数据集的实验结果表明WSM方法的平均匹配精确率达到92%,在匹配数量和精确率上优于常用的特征匹配方法,验证了该方法的有效性和鲁棒性。

关键词: 特征匹配, 相似性度量, 尺度不变特征变换, Canny算法, 古建筑图像

CLC Number: