Aggregating Gradient Distributions into Intensity Orders: A Novel Local Image Descriptor

Bin Fan, Fuchao Wu and Zhanyi Hu

National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences
A novel local image descriptor is proposed in this paper, which combines intensity orders and gradient distributions in multiple support regions. The novelty lies in three aspects: 1) The gradient is calculated in a rotation invariant way in a given support region; 2) The rotation invariant gradients are adaptively pooled spatially based on intensity orders in order to encode spatial information; 3) Multiple support regions are used for constructing descriptor which further improves its discriminative ability. Therefore, the proposed descriptor encodes not only gradient information but also information about relative relationship of intensities as well as spatial information. In addition, it is truly rotation invariant in theory without the need of computing a dominant orientation which is a major error source of most existing methods, such as SIFT. Results on the standard Oxford dataset and 3D objects have shown a significant improvement over the state-of-the-art methods under various image transformations. [video]

The experimental data used for evaluation can be downloaded from the Oxford University.

The affine covariant region detector (e.g., Harris-Affine or Hessian-Affine) can be downloaded from the Oxford University too.

The binary code of our method and matlab codes for performance evaluation are here.　

2012.10, The source code is available! Download now.

Comparison with SIFT and DAISY