`

Timezone: »

 
Poster
Heavy-tailed Distances for Gradient Based Image Descriptors
Yangqing Jia · Trevor Darrell

Wed Dec 14 08:45 AM -- 02:59 PM (PST) @ None #None
in Poster Session »

Many applications in computer vision measure the similarity between images or image patches based on some statistics such as oriented gradients. These are often modeled implicitly or explicitly with a Gaussian noise assumption, leading to the use of the Euclidean distance when comparing image descriptors. In this paper, we show that the statistics of gradient based image descriptors often follow a heavy-tailed distribution, which undermines any principled motivation for the use of Euclidean distances. We advocate for the use of a distance measure based on the likelihood ratio test with appropriate probabilistic models that fit the empirical data distribution. We instantiate this similarity measure with the Gamma-compound-Laplace distribution, and show significant improvement over existing distance measures in the application of SIFT feature matching, at relatively low computational cost.

[ PDF] 

Author Information

Yangqing Jia (Alibaba Group)
Trevor Darrell (UC Berkeley)

More from the Same Authors