Supervised two-step hash learning for efficient image retrieval

Xinhui Wu, Seiichiro Kamata, Lizhuang Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.

Original languageEnglish
Title of host publicationProceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages190-195
Number of pages6
ISBN (Electronic)9781538633540
DOIs
Publication statusPublished - 2018 Dec 13
Event4th Asian Conference on Pattern Recognition, ACPR 2017 - Nanjing, China
Duration: 2017 Nov 262017 Nov 29

Other

Other4th Asian Conference on Pattern Recognition, ACPR 2017
CountryChina
CityNanjing
Period17/11/2617/11/29

Fingerprint

Image retrieval
Labels
Neural networks
Experiments
Deep learning

Keywords

  • hash learning
  • image retrieval
  • prototype code

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wu, X., Kamata, S., & Ma, L. (2018). Supervised two-step hash learning for efficient image retrieval. In Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017 (pp. 190-195). [8575821] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACPR.2017.83

Supervised two-step hash learning for efficient image retrieval. / Wu, Xinhui; Kamata, Seiichiro; Ma, Lizhuang.

Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 190-195 8575821.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, X, Kamata, S & Ma, L 2018, Supervised two-step hash learning for efficient image retrieval. in Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017., 8575821, Institute of Electrical and Electronics Engineers Inc., pp. 190-195, 4th Asian Conference on Pattern Recognition, ACPR 2017, Nanjing, China, 17/11/26. https://doi.org/10.1109/ACPR.2017.83
Wu X, Kamata S, Ma L. Supervised two-step hash learning for efficient image retrieval. In Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 190-195. 8575821 https://doi.org/10.1109/ACPR.2017.83
Wu, Xinhui ; Kamata, Seiichiro ; Ma, Lizhuang. / Supervised two-step hash learning for efficient image retrieval. Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 190-195
@inproceedings{11a3a5ae857b4b12bd49c4562346fe3c,
title = "Supervised two-step hash learning for efficient image retrieval",
abstract = "Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.",
keywords = "hash learning, image retrieval, prototype code",
author = "Xinhui Wu and Seiichiro Kamata and Lizhuang Ma",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/ACPR.2017.83",
language = "English",
pages = "190--195",
booktitle = "Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Supervised two-step hash learning for efficient image retrieval

AU - Wu, Xinhui

AU - Kamata, Seiichiro

AU - Ma, Lizhuang

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.

AB - Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.

KW - hash learning

KW - image retrieval

KW - prototype code

UR - http://www.scopus.com/inward/record.url?scp=85059037615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059037615&partnerID=8YFLogxK

U2 - 10.1109/ACPR.2017.83

DO - 10.1109/ACPR.2017.83

M3 - Conference contribution

AN - SCOPUS:85059037615

SP - 190

EP - 195

BT - Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -