File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TIP.2013.2294546
- Scopus: eid_2-s2.0-84893836262
- PMID: 24474370
- WOS: WOS:000331196900001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Sparse label-indicator optimization methods for image classification
Title | Sparse label-indicator optimization methods for image classification |
---|---|
Authors | |
Keywords | image classification sparsity semi-supervised learning multi-class Graph random walk with restart |
Issue Date | 2014 |
Citation | IEEE Transactions on Image Processing, 2014, v. 23, n. 3, p. 1002-1014 How to Cite? |
Abstract | Image label prediction is a critical issue in computer vision and machine learning. In this paper, we propose and develop sparse label-indicator optimization methods for image classification problems. Sparsity is introduced in the label-indicator such that relevant and irrelevant images with respect to a given class can be distinguished. Also, when we deal with multi-class image classification problems, the number of possible classes of a given image can also be constrained to be small in which it is valid for natural images. The resulting sparsity model can be formulated as a convex optimization problem, and it can be solved very efficiently. Experimental results are reported to illustrate the effectiveness of the proposed model, and demonstrate that the classification performance of the proposed method is better than the other testing methods in this paper. © 2014 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/276979 |
ISSN | 2023 Impact Factor: 10.8 2023 SCImago Journal Rankings: 3.556 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jing, Liping | - |
dc.contributor.author | Ng, Michael K. | - |
dc.date.accessioned | 2019-09-18T08:35:14Z | - |
dc.date.available | 2019-09-18T08:35:14Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | IEEE Transactions on Image Processing, 2014, v. 23, n. 3, p. 1002-1014 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | http://hdl.handle.net/10722/276979 | - |
dc.description.abstract | Image label prediction is a critical issue in computer vision and machine learning. In this paper, we propose and develop sparse label-indicator optimization methods for image classification problems. Sparsity is introduced in the label-indicator such that relevant and irrelevant images with respect to a given class can be distinguished. Also, when we deal with multi-class image classification problems, the number of possible classes of a given image can also be constrained to be small in which it is valid for natural images. The resulting sparsity model can be formulated as a convex optimization problem, and it can be solved very efficiently. Experimental results are reported to illustrate the effectiveness of the proposed model, and demonstrate that the classification performance of the proposed method is better than the other testing methods in this paper. © 2014 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Image Processing | - |
dc.subject | image classification | - |
dc.subject | sparsity | - |
dc.subject | semi-supervised learning | - |
dc.subject | multi-class | - |
dc.subject | Graph | - |
dc.subject | random walk with restart | - |
dc.title | Sparse label-indicator optimization methods for image classification | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TIP.2013.2294546 | - |
dc.identifier.pmid | 24474370 | - |
dc.identifier.scopus | eid_2-s2.0-84893836262 | - |
dc.identifier.volume | 23 | - |
dc.identifier.issue | 3 | - |
dc.identifier.spage | 1002 | - |
dc.identifier.epage | 1014 | - |
dc.identifier.isi | WOS:000331196900001 | - |
dc.identifier.issnl | 1057-7149 | - |