FastRanDSac——一种高效的误匹配检测算法
FastRanDSac——a fast mismatching elimination algorithm

图像之间存在光照变化、旋转、仿射变换，使得局部特征匹配后，误匹配无法避免. 在正确匹配过半的前提下，提出一种简化的误匹配去除算法FastRanDSac，用于在极短时间内解决图像匹配对之间误匹配点的问题. 初步实验表明，在平移、旋转、尺度缩放、视角以及光照变化的图像中，FastRanDSac能保存近100%的正确匹配对，而运行速度与RANSAC相比有大幅度的提高.
Mismatching always exists after matching with local features due to the influences of illumination change，rotation，as well as affine transformation. This work focuses on improving the efficiency of mismatching elimination providing more than half of matching-pairs are correct. A fast random double sample consensus algorithm，called FastRanDSac，is proposed to eliminate the mismatching in a very short time. The power of the methods is that it can keep most correct matching-points while removes all the mismatching-points，and greatly improves the efficiency against RANSAC