BROWSE
Detail
Conference Paper
Extensive Analysis of Feature Selection for Compact Descriptor
Cited 5 time in 
Share 
Share
- Authors
- Keundong Lee, Seungjae Lee, Sang-il Na, Sungkwan Je, Weon-Geun Oh
- Issue Date
- 2013-01
- Citation
- Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2013, pp.53-57
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, feature selection criteria of local descriptors are examined with well-defined evaluation framework in MPEG-7 compact descriptor for visual search (CDVS) [6]. The effect of feature selection on descriptor was analyzed in compressed and uncompressed domain. Various combinations of feature characteristics such as scale and orientation of features, distance from center, and response of difference of Gaussian (DoG) [5] were examined for feature selection criterion via pair-wise matching experiments in MPEG-7 CDVS datasets. © 2013 IEEE.
- KSP Keywords
- Compressed and Uncompressed, Difference of Gaussian(DoG), Local descriptors, MPEG-7, Pair-wise matching, Scale and orientation, Selection criteria, Selection criterion, Visual search, Well-defined, evaluation framework