特征检测
文章平均质量分 79
linyunzju
这个作者很懒,什么都没留下…
展开
-
Canny边界检测实现
Canny's Edge Detector: ImplementationCanny's Edge Detector is well known for its ability to generate single-picel thick continuous edges. It consists of four major steps, which are described below, along with interesting implementation details and outputs.原创 2011-05-11 15:42:00 · 1865 阅读 · 0 评论 -
Canny边界检查算法导引
<br /><br />This tutorial will teach you how to:<br />(1) Implement the Canny edge detection algorithm. INTRODUCTION<br />Edges characterize boundaries and are therefore a problem of fundamental importance i转载 2011-05-11 15:04:00 · 1023 阅读 · 0 评论 -
SIFT程序源码下载地址
第一个链接地址是David Lowe自己写的官方版本(matlab code),运行起来效率非常高,达到了他论文Distinctive image features from scale-invariant keypoints中所写的“near real-time performance”,看来Davide Lowe花了不少力气对程序做了大量的优化,为什么这么说呢,因为我找到的另一个程序(第二个链接地址)计算SIFT特征向量的时间要远远长于Davide Lowe的官方版。可遗憾的是官方版没有提供核心的S原创 2011-04-28 15:44:00 · 9705 阅读 · 3 评论 -
SIFT 第六步: 生成SIFT特征
Now for the final step of SIFT. Till now, we had scale and rotation invariance. Now we create a fingerprint for each keypoint. This is to identify a keypoint. If an eye is a keypoint, then using this fingerprint, we’ll be able to distinguish it from other原创 2011-04-28 15:21:00 · 3068 阅读 · 0 评论 -
SIFT第五步:分配特征点的方向
<br />After step 4, we have legitimate key points. They’ve been tested to be stable. We already know the scale at which the keypoint was detected (it’s the same as the scale of the blurred image). So we have scale invariance. The next thing is to assign an原创 2011-04-22 22:38:00 · 2763 阅读 · 0 评论 -
SIFT第三步:找到特征点
Up till now, we have generated a scale space and used the scale space to calculate the Difference of Gaussians. Those are then used to calculate Laplacian of Gaussian approximations that is scale invariant. I told you that they produce great key points. He原创 2011-04-22 22:33:00 · 2759 阅读 · 0 评论 -
SIFT第二步:Laplacian of Gaussian近似
<br /><br />In the previous step , we created the scale space of the image. The idea was to blur an image progressively, shrink it, blur the small image progressively and so on. Now we use those blurred images to generate another set of images, the Differe原创 2011-04-22 22:30:00 · 4447 阅读 · 1 评论 -
SIFT第一步:创建scale space
Real world objects are meaningful only at a certain scale. You might see a sugar cube perfectly on a table. But if looking at the entire milky way, then it simply does not exist. This multi-scale nature of objects is quite common in nature. And a scale spa原创 2011-04-22 22:27:00 · 5691 阅读 · 3 评论 -
SIFT第四步:消除边界和低对比度的特征
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原创 2011-04-22 22:36:00 · 4319 阅读 · 0 评论 -
SIFT特征详细描述 上
一、介绍 特征的检测和匹配在许多计算机视觉应用中是一个重要的组成部分,例如无缝拼接,三维重建等。其中兴趣点特征是很重要的一类特征,而目前应用最广泛的兴趣点特征检测方法就是SIFT检测算法,该检测算法所得到的特征点不仅在位置上能够稳定识别,而且具有尺度不变性和旋转不变性。由于各大论坛以及该论文作者都只是给出matlab的实现算法,并未给出C++的版本,而且由于在SIFT的实现过程中有很多参数设置和原创 2011-06-15 14:23:00 · 3682 阅读 · 2 评论 -
OpenCV中SIFT的实现
出自:http://www.aishack.in/2010/05/sift-step-1-constructing-a-scale-space/Matching features across different images in a common problem in c转载 2011-04-22 22:24:00 · 14088 阅读 · 3 评论