Improvements of Local Descriptor in HOG/SIFT by BOF Approach

Zhouxin YANG; Takio KURITA

doi:10.1587/transinf.E97.D.1293

Improvements of Local Descriptor in HOG/SIFT by BOF Approach

Zhouxin YANG, Takio KURITA

Full Text Views

0

Share
Cite this

Summary :

Numerous studies have been focusing on the improvement of bag of features (BOF), histogram of oriented gradient (HOG) and scale invariant feature transform (SIFT). However, few works have attempted to learn the connection between them even though the latter two are widely used as local feature descriptor for the former one. Motivated by the resemblance between BOF and HOG/SIFT in the descriptor construction, we improve the performance of HOG/SIFT by a) interpreting HOG/SIFT as a variant of BOF in descriptor construction, and then b) introducing recently proposed approaches of BOF such as locality preservation, data-driven vocabulary, and spatial information preservation into the descriptor construction of HOG/SIFT, which yields the BOF-driven HOG/SIFT. Experimental results show that the BOF-driven HOG/SIFT outperform the original ones in pedestrian detection (for HOG), scene matching and image classification (for SIFT). Our proposed BOF-driven HOG/SIFT can be easily applied as replacements of the original HOG/SIFT in current systems since they are generalized versions of the original ones.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.5 pp.1293-1303

Publication Date: 2014/05/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.1293

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Zhouxin YANG
Hiroshima University
Takio KURITA
Hiroshima University

Keyword

bag of features, connection with HOG/SIFT, pedestrian detection, scene matching, image classification

Cite this

Copy

Zhouxin YANG, Takio KURITA, "Improvements of Local Descriptor in HOG/SIFT by BOF Approach" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 5, pp. 1293-1303, May 2014, doi: 10.1587/transinf.E97.D.1293.
Abstract: Numerous studies have been focusing on the improvement of bag of features (BOF), histogram of oriented gradient (HOG) and scale invariant feature transform (SIFT). However, few works have attempted to learn the connection between them even though the latter two are widely used as local feature descriptor for the former one. Motivated by the resemblance between BOF and HOG/SIFT in the descriptor construction, we improve the performance of HOG/SIFT by a) interpreting HOG/SIFT as a variant of BOF in descriptor construction, and then b) introducing recently proposed approaches of BOF such as locality preservation, data-driven vocabulary, and spatial information preservation into the descriptor construction of HOG/SIFT, which yields the BOF-driven HOG/SIFT. Experimental results show that the BOF-driven HOG/SIFT outperform the original ones in pedestrian detection (for HOG), scene matching and image classification (for SIFT). Our proposed BOF-driven HOG/SIFT can be easily applied as replacements of the original HOG/SIFT in current systems since they are generalized versions of the original ones.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.1293/_p

Copy

@ARTICLE{e97-d_5_1293,
author={Zhouxin YANG, Takio KURITA, },
journal={IEICE TRANSACTIONS on Information},
title={Improvements of Local Descriptor in HOG/SIFT by BOF Approach},
year={2014},
volume={E97-D},
number={5},
pages={1293-1303},
abstract={Numerous studies have been focusing on the improvement of bag of features (BOF), histogram of oriented gradient (HOG) and scale invariant feature transform (SIFT). However, few works have attempted to learn the connection between them even though the latter two are widely used as local feature descriptor for the former one. Motivated by the resemblance between BOF and HOG/SIFT in the descriptor construction, we improve the performance of HOG/SIFT by a) interpreting HOG/SIFT as a variant of BOF in descriptor construction, and then b) introducing recently proposed approaches of BOF such as locality preservation, data-driven vocabulary, and spatial information preservation into the descriptor construction of HOG/SIFT, which yields the BOF-driven HOG/SIFT. Experimental results show that the BOF-driven HOG/SIFT outperform the original ones in pedestrian detection (for HOG), scene matching and image classification (for SIFT). Our proposed BOF-driven HOG/SIFT can be easily applied as replacements of the original HOG/SIFT in current systems since they are generalized versions of the original ones.},
keywords={},
doi={10.1587/transinf.E97.D.1293},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Improvements of Local Descriptor in HOG/SIFT by BOF Approach
T2 - IEICE TRANSACTIONS on Information
SP - 1293
EP - 1303
AU - Zhouxin YANG
AU - Takio KURITA
PY - 2014
DO - 10.1587/transinf.E97.D.1293
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2014
AB - Numerous studies have been focusing on the improvement of bag of features (BOF), histogram of oriented gradient (HOG) and scale invariant feature transform (SIFT). However, few works have attempted to learn the connection between them even though the latter two are widely used as local feature descriptor for the former one. Motivated by the resemblance between BOF and HOG/SIFT in the descriptor construction, we improve the performance of HOG/SIFT by a) interpreting HOG/SIFT as a variant of BOF in descriptor construction, and then b) introducing recently proposed approaches of BOF such as locality preservation, data-driven vocabulary, and spatial information preservation into the descriptor construction of HOG/SIFT, which yields the BOF-driven HOG/SIFT. Experimental results show that the BOF-driven HOG/SIFT outperform the original ones in pedestrian detection (for HOG), scene matching and image classification (for SIFT). Our proposed BOF-driven HOG/SIFT can be easily applied as replacements of the original HOG/SIFT in current systems since they are generalized versions of the original ones.
ER -