Compressed Histogram of Gradients: A Low-Bitrate Descriptor

DMCA

Compressed Histogram of Gradients: A Low-Bitrate Descriptor (2011)

Cached

Download Links

by Vijay Chandrasekhar, Gabriel Takacs , David M. Chen , Sam S. Tsai , Yuriy Reznik , Radek Grzeszczuk , Bernd Girod

Venue:	INT J COMPUT VIS
Citations:	101 - 25 self

BibTeX

@MISC{Chandrasekhar11compressedhistogram,
    author = {Vijay Chandrasekhar and Gabriel Takacs and David M. Chen and Sam S. Tsai and Yuriy Reznik and Radek Grzeszczuk and Bernd Girod},
    title = {Compressed Histogram of Gradients: A Low-Bitrate Descriptor},
    year = {2011}
}

OpenURL

Abstract

Establishing visual correspondences is an essential component of many computer vision problems, which is often done with local feature-descriptors. Transmission and storage of these descriptors are of critical importance in the context of mobile visual search applications. We propose a framework for computing low bit-rate feature descriptors with a 20 × reduction in bit rate compared to state-of-the-art descriptors. The framework offers low complexity and has significant speed-up in the matching stage. We show how to efficiently compute distances between descriptors in the compressed domain eliminating the need for decoding. We perform a comprehensive performance comparison with SIFT, SURF, BRIEF, MPEG-7 image signatures and other low bit-rate descriptors and show that our proposed CHoG descriptor outperforms existing schemes significantly over a wide range of bitrates. We implement the descriptor in a mobile image retrieval system and for a database of 1 million CD, DVD and book covers, we achieve 96 % retrieval accuracy using only 4 KB of data per query image.

Keyphrases

low-bitrate descriptor wide range framework offer low complexity low bit-rate descriptor low bit-rate feature descriptor query image mpeg-7 image signature compressed domain bit rate chog descriptor essential component state-of-the-art descriptor mobile visual search application many computer vision problem comprehensive performance comparison retrieval accuracy visual correspondence mobile image retrieval system local feature-descriptors book cover critical importance significant speed-up matching stage

DMCA