OPT OpenIR  > 光学影像学习与分析中心
Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework
Xia, Yingjie1; Zhang, Luming2; Meng, Lei3; Yan, Yan4,5; Nie, Liqiang6; Li, Xuelong7
Contribution Rank7

To benefit the skin care, this paper aims to design an automatic and effective visual analysis framework, with the expectation of recognizing the skin disease from a given image conveying the disease affected surface. This task is nontrivial, since it is hard to collect sufficient well-labeled samples. To address such problem, we present a novel transfer learning model, which is able to incorporate external knowledge obtained from the rich and relevant Web images contributed by grassroots. In particular, we first construct a target domain by crawling a small set of images from vertical and professional dermatological websites. We then construct a source domain by collecting a large set of skin disease related images from commercial search engines. To reinforce the learning performance in the target domain, we initially build a learning model in the target domain, and then seamlessly leverage the training samples in the source domain to enhance this learning model. The distribution gap between these two domains are bridged by a linear combination of Gaussian kernels. Instead of training models with low-level features, we resort to deep models to learn the succinct, invariant, and high-level image representations. Different from previous efforts that focus on a few types of skin diseases with a small and confidential set of images generated from hospitals, this paper targets at thousands of commonly seen skin diseases with publicly accessible Web images. Hence the proposed model is easily repeatable by other researchers and extendable to other disease types. Extensive experiments on a real-world dataset have demonstrated the superiority of our proposed method over the state-of-the-art competitors.

KeywordSkin Disease Inference Transfer Learning
Indexed BySCI ; EI
WOS IDWOS:000447825400005
EI Accession Number20174704417356
Citation statistics
Document Type期刊论文
Corresponding AuthorZhang, Luming
Affiliation1.Zhejiang Univ, Coll Comp Sci, Hangzhou 310027, Zhejiang, Peoples R China
2.Hefei Univ Technol, Dept Elect Engn & Informat Syst, Hefei 230009, Anhui, Peoples R China
3.Nanyang Technol Univ, Joint NTU UBC Res Ctr Excellence Act Living Elder, Singapore, Singapore
4.Univ Trento, Dept Informat Engn & Comp Sci, I-38123 Trento, Italy
5.Adv Digital Sci Ctr, Singapore 138632, Singapore
6.Shandong Univ, Sch Comp Sci & Technol, Jinan, Shandong, Peoples R China
7.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt Imagery Anal & Learning, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Xia, Yingjie,Zhang, Luming,Meng, Lei,et al. Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(11):3080-3091.
APA Xia, Yingjie,Zhang, Luming,Meng, Lei,Yan, Yan,Nie, Liqiang,&Li, Xuelong.(2018).Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework.IEEE TRANSACTIONS ON CYBERNETICS,48(11),3080-3091.
MLA Xia, Yingjie,et al."Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework".IEEE TRANSACTIONS ON CYBERNETICS 48.11(2018):3080-3091.
Files in This Item:
File Name/Size DocType Version Access License
Exploring Web Images(1556KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xia, Yingjie]'s Articles
[Zhang, Luming]'s Articles
[Meng, Lei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xia, Yingjie]'s Articles
[Zhang, Luming]'s Articles
[Meng, Lei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xia, Yingjie]'s Articles
[Zhang, Luming]'s Articles
[Meng, Lei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Exploring Web Images to Enhance Skin Disease Analysis Under A Computer Vision Framework.pdf
Format: Adobe PDF
All comments (0)
No comment.

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