4.6 Article

Local Feature Descriptor for Image Matching: A Survey

期刊

IEEE ACCESS
卷 7, 期 -, 页码 6424-6434

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2018.2888856

关键词

Local feature descriptor; image matching; point pattern matching; pattern recognition

资金

  1. National Natural Science Foundation of China [61702251, 61363049, 61703115, 61673125, 61501286]
  2. State Scholarship Fund of China Scholarship Council (CSC) [201708360040]
  3. Natural Science Basic Research Plan in Shaanxi Province of China [2018JM6030]
  4. Key Research and Development Program in Shaanxi Province of China [2018GY-008]
  5. Fundamental Research Funds for the Central Universities [GK201702015]
  6. Doctor Scientific Research Starting Foundation of Northwest University [338050050]
  7. Youth Academic Talent Support Program of Northwest University
  8. Natural Science Foundation of Jiangxi Province [20161BAB212033]

向作者/读者索取更多资源

Image registration is an important technique in many computer vision applications such as image fusion, image retrieval, object tracking, face recognition, change detection and so on. Local feature descriptors, i.e., how to detect features and how to describe them, play a fundamental and important role in image registration process, which directly influence the accuracy and robustness of image registration. This paper mainly focuses on the variety of local feature descriptors including some theoretical research, mathematical models, and methods or algorithms along with their applications in the context of image registration. The existing local feature descriptors are roughly classified into six categories to demonstrate and analyze comprehensively their own advantages. The current and future challenges of local feature descriptors are discussed. The major goal of the paper is to present a unique survey of the state-of-the-art image matching methods based on feature descriptor, from which future research may benefit.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据