Compressed Histogram of Gradients: A Low-Bitrate Descriptor

被引:102
作者
Chandrasekhar, Vijay [1 ]
Takacs, Gabriel [1 ]
Chen, David M. [1 ]
Tsai, Sam S. [1 ]
Reznik, Yuriy [1 ]
Grzeszczuk, Radek [1 ]
Girod, Bernd [1 ]
机构
[1] Stanford Univ, Stanford, CA 94305 USA
关键词
CHoG; Feature descriptor; Mobile visual search; Content-based image retrieval; Histogram-of-gradients; Low bitrate;
D O I
10.1007/s11263-011-0453-z
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
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 20x 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.
引用
收藏
页码:384 / 399
页数:16
相关论文
共 49 条
[1]
[Anonymous], 2006, PROC EUR C COMPUT VI
[2]
[Anonymous], 2005, Ph.D. thesis
[3]
[Anonymous], P IEEE INT C AC SPEE
[4]
[Anonymous], 2010, P INT MOB MULT WORKS
[5]
[Anonymous], 2008, P IEEE C COMP VIS PA
[6]
[Anonymous], 2006, P IEEE COMPUTER SOC
[7]
[Anonymous], P NEUR INF PROC SYST
[8]
[Anonymous], 2009, PROC SPIE
[9]
[Anonymous], P EUR C COMP VIS ECC
[10]
[Anonymous], 2010, P EUR C COMP VIS ECC