WLD: A Robust Local Image Descriptor.

Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, Wen GaoIEEE TPAMI 2010 · OpenReview

Abstract

Inspired by Weber's Law, this paper proposes a simple, yet very powerful and robust local descriptor, called the Weber Local Descriptor (WLD). It is based on the fact that human perception of a pattern depends not only on the change of a stimulus (such as sound, lighting) but also on the original intensity of the stimulus. Specifically, WLD consists of two components: differential excitation and orientation. The differential excitation component is a function of the ratio between two terms: One is the relative intensity differences of a current pixel against its neighbors, the other is the intensity of the current pixel. The orientation component is the gradient orientation of the current pixel. For a given image, we use the two components to construct a concatenated WLD histogram. Experimental results on the Brodatz and KTH-TIPS2-a texture databases show that WLD impressively outperforms the other widely used descriptors (e.g., Gabor and SIFT). In addition, experimental results on human face detection also show a promising performance comparable to the best known results on the MIT+CMU frontal face test set, the AR face data set, and the CMU profile test set.
BibTeX
@article{chen2010wld,
  author = {Jie Chen and Shiguang Shan and Chu He and Guoying Zhao and Matti Pietikäinen and Xilin Chen and Wen Gao},
  title = {{WLD: A Robust Local Image Descriptor.}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2010},
  url = {https://openreview.net/forum?id=SixxvGXHxuTS},
}

Loading related content...

Figure