Vijay Chandrasekhar - Software

Compressed Histogram of Gradients

alt text 

For many mobile visual search applications, a query photo is taken by a mobile device and compared against a database on a remote server. The size of the data sent over the network needs to be as small as possible to reduce latency and improve user experience. We have studied descriptor compression techniques and shown that compressed descriptors can reduce query latency significantly in mobile image retrieval systems. Here, we make publicly available a Linux binary of a new low bitrate descriptor called Compressed Histogram of Gradients (CHoG), with the feature-location coding scheme cited below.

Download Link

  1. Dataset ( Link)

  2. V. Chandrasekhar, G. Takacs, D. M. Chen, S. S. Tsai, R. Grzeszczuk, Y. Reznik, and B. Girod, "Compressed Histogram of Gradients: A low bitrate descriptor", Proceedings of Special Issue on Mobile Vision, International Journal on Computer Vision, 2011. (Paper)

  3. S. Tsai, D. Chen, Gabriel Takacs, Vijay Chandrasekhar, Jatinder Singh, B. Girod, "Location Coding for Mobile Image Retrieval Systems", Proceedings of Mobimedia, London, UK, September 2009. (Paper)