原文地址http://www.image-net.org/download-features
We currently provide densely sampled SIFT[1] features. We provide raw SIFT descriptors as well as quantized codewords. Spatial coordiates of each descriptor/codeword are also included. The quantized codewords are suitable for Bag of Words representations[2][3]. The features are packaged as Matlab files and can be freely downloaded ( no signing-in is required ). Details are as follows:
Each image is resized to have a max side length of no more than 300 pixel. SIFT descriptors are computed on 20x20 overlapping patches with a spacing of 10 pixels. Images are further downsized (to 1/2 the side length and then 1/4 of the side length) and more descriptors are computed. We use the VLFeat [4] implemenation of dense SIFT (version 0.9.4.1).- David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004. pdf
- L. Fei-Fei and P. Perona, A Bayesian Hierarchical Model for Learning Natural Scene Categories. IEEE Comp. Vis. Patt. Recog. 2005. pdf
- Svetlana Lazebnik, Cordelia Schmid and Jean Ponce, Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. IEEE Comp. Vis. Patt. Recog. 2006. pdf
- A. Vedaldi and B. Fulkerson. VLFeat: An Open and Portable Library of Computer Vision Algorithms. 2008.http://www.vlfeat.org
How to download?
- We have not yet released SIFT features for all synsets. To check the list of synsets with SIFT features released, please use the API:
- http://www.image-net.org/api/text/imagenet.sbow.obtain_synset_list
- When you browse ImageNet from the Explore page, you can download the bag of visual words (sbow) feature of a synset if there is an icon "Download BoW Feature" below the image view panel.
- http://www.image-net.org/api/download/imagenet.sbow.synset?wnid=[wnid]
Code for computing the features
- The code used to computing the features has been released in the development kit of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC2010). Please consult the readme file in the kit for details.