SIFT第四步：消除边界和低对比度的特征

原创

于 2011-04-22 22:36:00 发布 · 4.4k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#image #math #less #features #matrix #idea

SIFT算法中，为了提升效率和鲁棒性，会去除边界和低对比度的特征。对于低对比度特征，若DoG图像中像素点的强度小于阈值则被剔除。对于可能位于边缘的特征，通过计算互相垂直的两个梯度，如果两者都足够大则视为角点保留，否则剔除。这一过程利用了Hessian矩阵来判断。经过这两步，筛选出更优质的特征点。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Key points generated in the previous step produce a lot of key points. Some of them lie along an edge, or they don’t have enough contrast. In both cases, they are not useful as features. So we get rid of them. The approach is similar to the one used in the Harris Corner Detector for removing edge features. For low contrast features, we simply check their intensities.

Removing low contrast features

This is simple. If the magnitude of the intensity (i.e., without sign) at the current pixel in the DoG image (that is being checked for minima/maxima) is less than a certain value, it is rejected.

Because we have subpixel keypoints (we used the Taylor expansion to refine keypoints), we again need to use the taylor expansion to get the intensity value at subpixel locations. If it’s magnitude is less than a certain value, we reject the keypoint.