The Scale-Invariant Feature Transform (SIFT) bundles(捆绑) a feature detector and a feature descriptor.

The detector extracts from an image a number of frames (attributed regions) in a way which is consistent with (some) variations of the illumination, viewpoint and other viewing conditions.

The descriptor associates to the regions a signature(标志) which identifies their appearance compactly(紧密) and robustly. For a more in-depth description of the algorithm, see our API reference for SIFT.

(SIFT是一个很好的特征检测器，它能够从一张图片中检测出一组不受光照、视线等影响的特征点。同时它本身就是一个很好的特征描述子，它能够充分反映特征点附近局部图像的形状和纹理结构特性，具有较好的鲁棒性和独特性)

(本博客系原创，转载请注明出处：http://www.cnblogs.com/pfli1995/p/4657302.html)

(博主cnds中对应文章：http://blog.csdn.net/xuexiyanjiusheng/article/details/46944395)

Extracting frames and descriptors

Both the detector and descriptor are accessible by the vl_sift MATLAB command (there is a similar command line utility). Open MATLAB and load a test image

I = vl_impattern(‘roofs1‘) ;
image(I) ;