Title :
Extensive analysis of feature selection for compact descriptor
Author :
Keundong Lee ; Seungjae Lee ; Sang-il Na ; Sungkwan Je ; Weon-Geun Oh
Author_Institution :
Creative Content Res. Lab., ETRI, Daejeon, South Korea
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.
Keywords :
Gaussian processes; feature extraction; image coding; CDVS; DoG; MPEG-7 compact descriptor for visual search; compact descriptor; difference of Gaussian; extensive analysis; feature characteristics; feature selection; local descriptors; Buildings; Feature extraction; Mobile communication; Probability; Transform coding; Visualization; compact descriptor; feature selection; mobile visual search;
Conference_Titel :
Frontiers of Computer Vision, (FCV), 2013 19th Korea-Japan Joint Workshop on
Conference_Location :
Incheon
Print_ISBN :
978-1-4673-5620-6
DOI :
10.1109/FCV.2013.6485459
