1、ubc:DAVID LOWE---SIFT算法的创始人，两篇巨经典经典的文章
http://www.cs.ubc.ca/~lowe/

2、cmu:YanKe---PCASIFT,总结的SIFT方面的文章SO全，巨经典
http://www.andrew.cmu.edu/user/yke/

3、ubc:MBROWN---SIFT算法用于图像拼接的经典应用autopano-sift，包括一个SIFTLIB库
http://www.cs.ubc.ca/~mbrown/autostitch/autostitch.html
http://www.cs.ubc.ca/~mbrown/panorama/panorama.html

4、toronto:Jepson---Matlab SIFT tutorial, 超级超级超级经典~
http://www.cs.toronto.edu/~jepson

5、ucla:Vedaldi---加州大学一个博士生编的SIFT，Matlab、C的都有，但没用过
http://www.cs.ucla.edu/~vedaldi/

6、一个小的拼接软件ptasmblr
http://www.tawbaware.com/ptasmblr.htm

作为一种匹配能力较强的局部描述算子，SIFT算法的实现相当复杂，但从软件开发的角度来说，只要会使用其中几个比较重要的函数就行了。这里要感谢David Lowe这个大牛，不但提供了一种强悍的特征匹配算法，还给出了C++的实现代码，后来有人用C#实现了这个算法，需要的朋友可到网上自行下载。

关键函数一：   int sift_features( IplImage* img, struct feature** feat )

这个函数就是用来提取图像中的特征向量。参数img为一个指向IplImage数据类型的指针，用来表示需要进行特征提取的图像。IplImage是opencv库定义的图像基本类型（关于opencv是一个著名的图像处理类库，详细的介绍可以参见http://www.opencv.org.cn）。参数feat 是一个数组指针，用来存储图像的特征向量。函数调用成功将返回特征向量的数目，否则返回-1.

关键函数二：

int _sift_features( IplImage* img, struct feature** feat, int intvls,double sigma, double contr_thr, int curv_thr, int img_dbl, int descr_width, int descr_hist_bins )

这个函数是函数一的重载，作用是一样的，实际上函数一只不过是使用默认参数调用了函数二，核心的代码都是在函数二中实现的。下面将详细介绍一下其他的几个参数。

intvls: 每个尺度空间的采样间隔数，默认值为3.

sigma: 高斯平滑的数量，默认值1.6.

contr_thr:判定特征点是否稳定，取值（0，1），默认为0.04，这个值越大，被剔除的特征点就越多。

curv_thr:判定特征点是否边缘点，默认为6.

img_dbl:在建立尺度空间前如果图像被放大了1倍则取值为1，否则为0.

descr_width:计算特征描述符时邻域子块的宽度，默认为4.

descr_hist_bins:计算特征描述符时将特征点邻域进行投影的方向数，默认为8，分别是0，45，90，135，180，215，270，315共8个方向。

如果只是做特征提取，上面这个函数就足够了，不同图像之间的匹配都是建立在这个基础上的，如果你有足够强的编程能力即使不懂这个算法也能够编写出像样的程序来，因为下面的比较说白了都是数据结构的比较，跟算法已经没有太多关系了。如果想要深入了解算法，还是认真的看论文和代码吧。

============================================

SIFT: Scale Invariant Feature Transform

by Utkarsh in Computer Vision,Featured

Matching features across different images in a common problem in computer vision. When all images are similar in nature (same scale, orientation, etc) simple corner detectors can work. But when you have images of different scales and rotations, you need to use the Scale Invariant Feature Transform.

Why care about SIFT

SIFT isn’t just scale invariant. You can change the following, and still get good results:

• Scale (duh)
• Rotation
• Illumination
• Viewpoint

Here’s an example. We’re looking for these:

And we want to find these objects in this scene:

Here’s the result:

Now that’s some real robust image matching going on. The big rectangles mark matched images. The smaller squares are for individual features in those regions. Note how the big rectangles are skewed. They follow the orientation and perspective of the object in the scene.

The algorithm

SIFT is quite an involved algorithm. It has a lot going on and can become confusing, So I’ve split up the entire algorithm into multiple parts. Here’s an outline of what happens in SIFT.

1. Constructing a scale space
   This is the initial preparation. You create internal representations of the original image to ensure scale invariance. This is done by generating a “scale space”.
2. LoG Approximation
   The Laplacian of Gaussian is great for finding interesting points (or key points) in an image. But it’s computationally expensive. So we cheat and approximate it using the representation created earlier.
3. Finding keypoints
   With the super fast approximation, we now try to find key points. These are maxima and minima in the Difference of Gaussian image we calculate in step 2
4. Get rid of bad key points
   Edges and low contrast regions are bad keypoints. Eliminating these makes the algorithm efficient and robust. A technique similar to the Harris Corner Detector is used here.
5. Assigning an orientation to the keypoints
   An orientation is calculated for each key point. Any further calculations are done relative to this orientation. This effectively cancels out the effect of orientation, making it rotation invariant.
6. Generate SIFT features
   Finally, with scale and rotation invariance in place, one more representation is generated. This helps uniquely identify features. Lets say you have 50,000 features. With this representation, you can easily identify the feature you’re looking for (say, a particular eye, or a sign board).

That was an overview of the entire algorithm. Over the next few days, I’ll go through each step in detail. Finally, I’ll show you how to implement SIFT in OpenCV!