특징 추출을 이용한 이미지 매칭 기술의 최근 동향 분석

초록

Image matching is a field of basic computer vision technology meaning finding similar features by comparing two or more images. In addition, the importance of image matching is emphasized because it is used in various applications of various computer visions such as image search, image stitching, and image difference detection. Among them, image matching through feature extraction is the most widely used technique in the field of image matching. Recently, new techniques introduced with thet development of deep learning technologies that from the past rule-based techniques. In this paper, image matching technology through feature extraction is introduced by dividing it into two processes: feature, descriptor extraction and matching using feature descriptors. We also describe the process from existing rule-based techniques to recent techniques using deep learning. Finally, we analyze the performance of each technique through experimental results. Copyright Ⓒ 2023 Korean Institute of Broadcast and Media Engineers. All rights reserved. “This is an Open-Access article distributed under the terms of the Creative Commons BY-NC-ND (http://creativecommons.org/licenses/by-nc-nd/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and not altered.”

키워드