SIFT Feature Point Matching Based on Improved RANSAC Algorithm
Authors:
- Guangjun ShiGSGuangjun Shi
- Xiangyang XuXXXiangyang Xu
- Yaping DaiYDYaping Dai
- 1 August 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 474-477
Abstract
When matching the SIFT feature points, there will be lots of mismatches. The RANSAC algorithm can be used to remove the mismatches by finding the transformation matrix of these feature points. But when the data space contains a lot of mismatches, finding the right transformation matrix will be very difficult. What's more, the probability of finding the error model is very large. Aiming at solving the problem, this paper proposed an improved RANSAC algorithm. Before using the RANSAC algorithm, we removed parts of the error feature points by two methods, one is eliminating features not belonging to the target area and the other is removing the crossing points. The two methods aimed to improve the proportion of feature points matched correctly. Experiments showed that, the improved RANSAC algorithm could find the model more accurately, improve efficiency, and make the feature point matching more accurately.Keywords
This publication has 5 references indexed in Scilit:
- Local feature view clustering for 3D object recognition2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Shape indexing using approximate nearest-neighbour search in high-dimensional spaces2002
- Object recognition from local scale-invariant features1999
- The fundamental matrix: Theory, algorithms, and stability analysisInternational Journal of Computer Vision, 1996