Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/108536
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | SLNSW-UTS: a historical image dataset for image multi-labeling and retrieval |
Author: | Zhang, J. Zhang, J. Lu, J. Shen, C. Curr, K. Phua, R. Neville, R. Edmonds, E. |
Citation: | Proceedings of the International Conference on Digital Image Computing: Techniques and Applications, 2016 / Liew, A.W.C., Lovell, B., Fookes, C., Zhou, J., Gao, Y., Blumenstein, M., Wang, Z. (ed./s), pp.1-6 |
Publisher: | IEEE |
Issue Date: | 2016 |
ISBN: | 9781509028962 |
Conference Name: | International Conference on Digital Image Computing Techniques and Applications (DICTA) (30 Nov 2016 - 2 Dec 2016 : Gold Coast, Qld) |
Editor: | Liew, A.W.C. Lovell, B. Fookes, C. Zhou, J. Gao, Y. Blumenstein, M. Wang, Z. |
Statement of Responsibility: | Junjie Zhang, Jian Zhang, Jianfeng Lu, Chunhua Shen, Kate Curr, Robin Phua, Richard Neville and Elise Edmonds |
Abstract: | This paper introduces a dataset of historical images created by the State Library of New South Wales and the University of Technology Sydney (UTS). The dataset has a total of 29713 images with 119 unique labels. Each image contains multiple labels. We use a CNN-based framework to explore the feasibility of our dataset in image multi-labeling and retrieval research, and extract semantic level image features for future research use. The experiment results illustrate that effective deep learning models can be trained on our dataset. We also introduce five applications that can be studied on our historical image dataset. |
Keywords: | Historical image; multi-labeling; retrieval; dataset construction |
Rights: | © 2016 IEEE |
DOI: | 10.1109/DICTA.2016.7797084 |
Published version: | http://dx.doi.org/10.1109/dicta.2016.7797084 |
Appears in Collections: | Aurora harvest 8 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_108536.pdf Restricted Access | Restricted Access | 1.17 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.