UM  > 科技學院  > 電腦及資訊科學系
An image classification method that considers privacy-preservation
Chongwen Liu1,2; Zhaowei Shang1,2; Yuan Yan Tang3
Source PublicationNeurocomputing
ISSN18728286 09252312

Using images that are dispersed in a network can improve image classification performance; however, it is easy to leak the image holders’ privacy. In this paper, we present a novel method that considers both image classification performance and the image holders’ privacy-preservation. Our method contains four stages; the feature extraction stage follows the Bag-of-Features (BoF) framework, but it introduces significantly novel stages in the training, classification and ensemble stages. In the training stage, we split the image classification into many one-vs.-one classification problems; a set of binary classifiers as weak learners are learned on a local machine, to classify each image in an autonomous system. In the classification stage, a local machine sends features of unlabeled images to each image autonomous system, and then, each image autonomous system and local machine finish a prediction task under their own trained model. Afterward, the image autonomous systems send their prediction labels back to the local system. In the ensemble stage, we gather all of the prediction labels from the image autonomous systems and design an ensemble system to ensemble them into final classification results. This ensemble system must consider both the efficiency of the different trained models in each image autonomous system and the efficiency of the trained model on each class in the one-vs.-one classification problems. During the whole process, only the features of unlabeled images and prediction labels are transmitted in the network, which largely reduces the risk of privacy leakage. We conducted experiments on the network environment, to prove that our method has preferable performance. Our first experiment demonstrates that the performance of our method achieves state-of-the-art performance on four public dataset benchmarks, which shows that our method has competitive performance. The second experiment shows that our method achieves state-of-the-art performance with even fewer training samples, which means that there is less communication overhead and better privacy-preservation.

KeywordEnsemble System Image Classification Privacy-preservation
URLView the original
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000382794300008
Fulltext Access
Citation statistics
Cited Times [WOS]:5   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
Corresponding AuthorChongwen Liu; Zhaowei Shang; Yuan Yan Tang
Affiliation1.Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University), Ministry of Education, China
2.College of Computer Science, Chongqing University, Chongqing, China
3.Faculty of Science and Technology, University of Macau, Macau, China
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Chongwen Liu,Zhaowei Shang,Yuan Yan Tang. An image classification method that considers privacy-preservation[J]. Neurocomputing,2016,208:80-98.
APA Chongwen Liu,Zhaowei Shang,&Yuan Yan Tang.(2016).An image classification method that considers privacy-preservation.Neurocomputing,208,80-98.
MLA Chongwen Liu,et al."An image classification method that considers privacy-preservation".Neurocomputing 208(2016):80-98.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chongwen Liu]'s Articles
[Zhaowei Shang]'s Articles
[Yuan Yan Tang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chongwen Liu]'s Articles
[Zhaowei Shang]'s Articles
[Yuan Yan Tang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chongwen Liu]'s Articles
[Zhaowei Shang]'s Articles
[Yuan Yan Tang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.