Codebook Learning for Image Recognition Based on Parallel Key SIFT Analysis

Feng YANG; Zheng MA; Mei XIE

doi:10.1587/transinf.2016EDL8167

Codebook Learning for Image Recognition Based on Parallel Key SIFT Analysis

Feng YANG, Zheng MA, Mei XIE

Full Text Views

0

Share
Cite this

Summary :

The quality of codebook is very important in visual image classification. In order to boost the classification performance, a scheme of codebook generation for scene image recognition based on parallel key SIFT analysis (PKSA) is presented in this paper. The method iteratively applies classical k-means clustering algorithm and similarity analysis to evaluate key SIFT descriptors (KSDs) from the input images, and generates the codebook by a relaxed k-means algorithm according to the set of KSDs. With the purpose of evaluating the performance of the PKSA scheme, the image feature vector is calculated by sparse code with Spatial Pyramid Matching (ScSPM) after the codebook is constructed. The PKSA-based ScSPM method is tested and compared on three public scene image datasets. The experimental results show the proposed scheme of PKSA can significantly save computational time and enhance categorization rate.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.4 pp.927-930

Publication Date: 2017/04/01

Publicized: 2017/01/10

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8167

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Feng YANG
  University of Electronic Science and Technology of China,Wenzhou Medical University
Zheng MA
  University of Electronic Science and Technology of China
Mei XIE
  University of Electronic Science and Technology of China

Keyword

codebook learning, image classification, parallel key SIFT analysis, ScSPM

Cite this

Copy

Feng YANG, Zheng MA, Mei XIE, "Codebook Learning for Image Recognition Based on Parallel Key SIFT Analysis" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 4, pp. 927-930, April 2017, doi: 10.1587/transinf.2016EDL8167.
Abstract: The quality of codebook is very important in visual image classification. In order to boost the classification performance, a scheme of codebook generation for scene image recognition based on parallel key SIFT analysis (PKSA) is presented in this paper. The method iteratively applies classical k-means clustering algorithm and similarity analysis to evaluate key SIFT descriptors (KSDs) from the input images, and generates the codebook by a relaxed k-means algorithm according to the set of KSDs. With the purpose of evaluating the performance of the PKSA scheme, the image feature vector is calculated by sparse code with Spatial Pyramid Matching (ScSPM) after the codebook is constructed. The PKSA-based ScSPM method is tested and compared on three public scene image datasets. The experimental results show the proposed scheme of PKSA can significantly save computational time and enhance categorization rate.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8167/_p

Copy

@ARTICLE{e100-d_4_927,
author={Feng YANG, Zheng MA, Mei XIE, },
journal={IEICE TRANSACTIONS on Information},
title={Codebook Learning for Image Recognition Based on Parallel Key SIFT Analysis},
year={2017},
volume={E100-D},
number={4},
pages={927-930},
abstract={The quality of codebook is very important in visual image classification. In order to boost the classification performance, a scheme of codebook generation for scene image recognition based on parallel key SIFT analysis (PKSA) is presented in this paper. The method iteratively applies classical k-means clustering algorithm and similarity analysis to evaluate key SIFT descriptors (KSDs) from the input images, and generates the codebook by a relaxed k-means algorithm according to the set of KSDs. With the purpose of evaluating the performance of the PKSA scheme, the image feature vector is calculated by sparse code with Spatial Pyramid Matching (ScSPM) after the codebook is constructed. The PKSA-based ScSPM method is tested and compared on three public scene image datasets. The experimental results show the proposed scheme of PKSA can significantly save computational time and enhance categorization rate.},
keywords={},
doi={10.1587/transinf.2016EDL8167},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - Codebook Learning for Image Recognition Based on Parallel Key SIFT Analysis
T2 - IEICE TRANSACTIONS on Information
SP - 927
EP - 930
AU - Feng YANG
AU - Zheng MA
AU - Mei XIE
PY - 2017
DO - 10.1587/transinf.2016EDL8167
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2017
AB - The quality of codebook is very important in visual image classification. In order to boost the classification performance, a scheme of codebook generation for scene image recognition based on parallel key SIFT analysis (PKSA) is presented in this paper. The method iteratively applies classical k-means clustering algorithm and similarity analysis to evaluate key SIFT descriptors (KSDs) from the input images, and generates the codebook by a relaxed k-means algorithm according to the set of KSDs. With the purpose of evaluating the performance of the PKSA scheme, the image feature vector is calculated by sparse code with Spatial Pyramid Matching (ScSPM) after the codebook is constructed. The PKSA-based ScSPM method is tested and compared on three public scene image datasets. The experimental results show the proposed scheme of PKSA can significantly save computational time and enhance categorization rate.
ER -