Improved SIFT Feature Extraction and Matching Based on Spectral Image Space

被引：0
|
作者：
Ding G. [1 ,2 ,3 ]
Qiao Y. [1 ]
Yi W. [1 ]
Du L. [1 ]
机构：
[1] Key Laboratory of Optical Calibration and Characterization, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei
[2] University of Science and Technology of China, Hefei
[3] North Automatic Control Technology Institute, Taiyuan
来源：
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology | 2022年 / 42卷 / 02期
关键词：
Double position criterion; Feature detection; Image matching; Scale invariant feature transform (SIFT); Spectral image space;
D O I：
10.15918/j.tbit1001-0645.2020.024
中图分类号：
学科分类号：
摘要：
As a method to measure the spatial properties of image, the Gaussian kernel with different parameters was used to get the difference in original SIFT algorithm, while the difference in the spectral dimension of optical system was used in the proposed method. Comparing with traditional sift method and a lot of improved methods, counting the image block pixel information only in the neighborhood around the feature points, the new method was arranged to divide the matching process into two steps. Firstly, the image block pixel information got from the neighborhood of the feature points was rough matched. And then four matching pairs with the highest similarity were selected as the benchmark matching pairs, and the feature points were checked twice. The simulation results show that the proposed method can significantly increase the number of detected feature points and effectively eliminate the error matching. Copyright ©2022 Transaction of Beijing Institute of Technology. All rights reserved.
引用
收藏
页码：192 / 199
页数：7
相关论文
共 16 条
  • [1] LI Heyu, WANG Qing, A real time sift feature extraction algorithm, Journal of Astronautics, 38, 8, pp. 865-871, (2017)
  • [2] PERSHAN R, ODINDI J, MUTANGA O., Feature level image fusion of optical imagery and synthetic aperture radar (SAR) for invasive alien plant species detection and mapping, Remote Sensing Applications Society & Environment, 10, pp. 198-208, (2018)
  • [3] PRIYALL, ANAND S., Object recognition and 3D reconstruction of occluded objects using binocular stereo, Cluster Computing, 21, 8, pp. 1-10, (2018)
  • [4] MORAVEC H P., Obstacle avoidance and navigation in the real world by a seeing robot rover, (1980)
  • [5] HARRIS C, STEPHENS M J., A combined corner and edge detector, Proceedings of the Fourth Alvey Vision Conference, pp. 147-152, (1988)
  • [6] DALAL N., Finding people in images and videos, (2006)
  • [7] LOWE D G., Distinctive image features from scale-invariant key points, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [8] PATRIK S, DAVID S., Progress in SIFT-MS: breath analysis and other applications, Mass Spectrometry Reviews, 30, 2, pp. 236-267, (2011)
  • [9] ASHOK A, ANZAR S M., Robust partial fingerprint recognition using wavelet SIFT descriptors, Pattern Analysis & Applications, 20, 2, pp. 1-17, (2017)
  • [10] RATHGEB C, WAGNER J, BUSCH C., SIFT-based iris recognition revisited: prerequisites, advantages and improvements, Pattern Analysis & Applications, 22, 11, pp. 1-18, (2018)
12