关闭

SIFT论文整理

标签: SIFTOpenCV
719人阅读 评论(0) 收藏 举报
分类:

Distinctive Image Featuresfrom Scale-Invariant Keypoints

本文主要是对Lowe SIFT论文的提炼,标注自己阅读论文时需要重点理解的知识点,以备日后回顾时,无需从头看论文。(仅供他人参考)

1. Introduction

  • Scale-space extrema detection:
  • Keypoint localization
  • Orientation assignment
  • Keypoint descriptor

…..

3. Detection of scale-space extrema

Detecting locations that areinvariant to scale change of the image can be accomplished by searching for stable featuresacross all possible scales, using a continuous function of scale known as scale space (Witkin,1983).

  • 构建尺度空间
    figure1
  • LoG近似DoG找到关键点<检测DOG尺度空间极值点> Figure 2

3.1 Local extrema detection

In order to detect the local maxima and minima of D(x, y, σ), each sample point is comparedto its eight neighbors in the current image and nine neighbors in the scale above and below(see Figure 2). It is selected only if it is larger than all of these neighbors or smaller than allof them. The cost of this check is reasonably low due to the fact that most sample points willbe eliminated following the first few checks.

Figure 3

3.2 Frequency of sampling in scale

​ To summarize, these experiments show that the scale-space difference-of-Gaussian func-tion has a large number of extrema and that it would be very expensive to detect them all.Fortunately, we can detect the most stable and useful subset even with a coarse sampling of scales.

3.3 Frequency of sampling in the spatial domain

Figure 4

Just as we determined the frequency of sampling per octave of scale space, so we must de-termine the frequency of sampling in the image domain relative to the scale of smoothing.Given that extrema can be arbitrarily close together, there will be a similar trade-off betweensampling frequency and rate of detection. Figure 4 shows an experimental determination ofthe amount of prior smoothing, σ, that is applied to each image level before building thescale space representation for an octave.

Of course, if we pre-smooth the image before extrema detection, we are effectively dis-carding the highest spatial frequencies. Therefore, to make full use of the input, the imagecan be expanded to create more sample points than were present in the original. We double the size of the input image using linear interpolation prior to building the first level ofthe pyramid.

4. Accurate keypoint localization

Once a keypoint candidate has been found by comparing a pixel to its neighbors, the nextstep is to perform a detailed fit to the nearby data for location, scale, and ratio of principalcurvatures. This information allows points to be rejected that have low contrast (and aretherefore sensitive to noise) or are poorly localized along an edge.

4.1 Eliminating edge responses

For stability, it is not sufficient to reject keypoints with low contrast. The difference-of-Gaussian function will have a strong response along edges, even if the location along theedge is poorly determined and therefore unstable to small amounts of noise.

5. Orientation assignment

By assigning a consistent orientation to each keypoint based on local image properties, the keypoint descriptor can be represented relative to this orientation and therefore achieve in-variance to image rotation. This approach contrasts with the orientation invariant descriptorsof Schmid and Mohr (1997), in which each image property is based on a rotationally invariant measure. The disadvantage of that approach is that it limits the descriptors that can be usedand discards image information by not requiring all measures to be based on a consistentrotation.

​ Peaks in the orientation histogram correspond to dominant directions of local gradients.The highest peak in the histogram is detected, and then any other local peak that is within 80% of the highest peak is used to also create a keypoint with that orientation. Therefore, forlocations with multiple peaks of similar magnitude, there will be multiple keypoints created atthe same location and scale but different orientations. Only about 15% of points are assignedmultiple orientations, but these contribute significantly to the stability of matching. Finally, aparabola is fit to the 3 histogram values closest to each peak to interpolate the peak positionfor better accuracy.

Figure 10

Figure 12

6. The local image descriptor - 给特征点赋值一个128维方向参数

Figure 13

Figure 15

6.1 Descriptor representation

Figure 7

7. Application to object recognition

7.1 Keypoint matching

Figure 11

7.2 Efficient nearest neighbor indexing

No algorithms are known that can identify the exact nearest neighbors of points in high di-mensional spaces that are any more efficient than exhaustive search. Our keypoint descriptorhas a 128-dimensional feature vector, and the best algorithms, such as the k-d tree (Friedmanet al., 1977) provide no speedup over exhaustive search for more than about 10 dimensionalspaces. Therefore, we have used an approximate algorithm, called the Best-Bin-First (BBF) algorithm (Beis and Lowe, 1997).

7.3 Clustering with the Hough transform

To maximize the performance of object recognition for small or highly occluded objects, wewish to identify objects with the fewest possible number of feature matches. We have foundthat reliable recognition is possible with as few as 3 features .

References

0
0
查看评论

Lowe关于SIFT的经典论文1

  • 2012-10-25 15:34
  • 336KB
  • 下载

sift论文看后理解

近来发现,只看论文是不行的,论文看完了,当时可能明白的马马虎虎,过几天在遇到这个东西,又忘记了,还是写点东西,记录下吧。 SIFT,即尺度不变特征变换(Scale-invariant feature transform,SIFT),该算法具有尺度不变性,对于旋转角度,图像亮度或拍摄角度改变具有一定的...
  • mysql403
  • mysql403
  • 2015-11-06 22:02
  • 1590

SIFT经典论文

  • 2012-11-23 20:12
  • 872KB
  • 下载

IJCV04 David.lowe Distinctive Image Features from Scale-Invariant Keypoints

  • 2013-06-27 21:35
  • 444KB
  • 下载

pycharm永久激活

pycharm是很强大的开发工具,但是每次注册着实让人头疼。网络上很多注册码、注册服务器等等、但都只是一年或者不能用;为次有如下解决方案。亲测有效!!!如果想让pycharm永久被激活,比如截止日到2099-01-01;这应该算是永久激活了吧;哈哈哈 step1:下载jar包: 次jar包的目的就是...
  • qq_32259579
  • qq_32259579
  • 2018-01-02 15:13
  • 27483

G语言

<br />  图形化的程序语言,又称为“G”语言。使用这种语言编程时,基本上不写程序代码,取而代之的是流程图。它尽可能利用了技术人员、科学家、工程师所熟悉 的术语、图标和概念,因此,LabVIEW是一个面向最终用户的工具。它可以增强你构建自己的科学和工程系统的能力,提供了实现仪器编程...
  • zzusimon
  • zzusimon
  • 2011-04-08 15:19
  • 5282

CSDN博客排名第一名,何许人也

CSDN博客排名第一名,何许人也一、提出问题CSDN博客排名第一名,何许人也。分析截止时间是:2013年12月19日星期四22:00。二、博客网址http://blog.csdn.net/phphot三、有图有真相四、博客分析1.博文文章数量分析博客注册日期是:2007年05月31日第一次发表博文的...
  • littletigerat
  • littletigerat
  • 2013-12-19 22:23
  • 20652

C# 和EmguCV

想实现界面化的图像/视频处理算法,发现EmguCV封装了OPencv库,支持C#等,于是按照网上教程下载/安装来试试。 http://blog.csdn.net/fioletfly/article/details/7329051 配置过程网上贴很多参考。 做了一个简单的界面,两个按钮,两个图片显示...
  • qq_27991659
  • qq_27991659
  • 2016-08-24 17:54
  • 2971

Java实现图片上传到服务器,并把上传的图片读取出来

插个广告,强烈推荐一个微信公众号“Java知音”,专注Java开发领域,每天定时推送优质技术文章,还有一些练手项目源码,视频学习资源等等,欢迎微信扫码关注!以下是正文:在很多的网站都可以实现上传头像,可以选择自己喜欢的图片做头像,从本地上传,下次登录时可以直接显示出已经上传的头像,那么这个是如何实现...
  • weixin_36380516
  • weixin_36380516
  • 2017-02-28 14:20
  • 39131

nodejs 升级后, vue+webpack 项目 node-sass 报错的解决方法

关于 node 环境升级到 v8^ 以上,node-sass 报错的解决方法今天给同事电脑升级了一下系统,顺便升级了所有的软件,发现原来好好的项目报错了。报错大致信息如下: ERROR Failed to compile with 1 errors ...
  • FungLeo
  • FungLeo
  • 2017-11-13 14:06
  • 2867
    个人资料
    • 访问:90015次
    • 积分:935
    • 等级:
    • 排名:千里之外
    • 原创:34篇
    • 转载:4篇
    • 译文:0篇
    • 评论:4条
    文章分类
    最新评论