Li, J. and Allinson, N. and Tao, D. and Li, Xuelong (2006) Multitraining support vector machine for image retrieval. IEEE Transactions on Image Processing 15 (11), pp. 3597-3601. ISSN 1057-7149.
Text (Publisher draft (Refereed))
Download (1674Kb) | Preview
Relevance feedback (RF) schemes based on support vector machines (SVMs) have been widely used in content-based image retrieval (CBIR). However, the performance of SVM-based RF approaches is often poor when the number of labeled feedback samples is small. This is mainly due to 1) the SVM classifier being unstable for small-size training sets because its optimal hyper plane is too sensitive to the training examples; and 2) the kernel method being ineffective because the feature dimension is much greater than the size of the training samples. In this paper, we develop a new machine learning technique, multitraining SVM (MTSVM), which combines the merits of the cotraining technique and a random sampling method in the feature space. Based on the proposed MTSVM algorithm, the above two problems can be mitigated. Experiments are carried out on a large image set of some 20 000 images, and the preliminary results demonstrate that the developed method consistently improves the performance over conventional SVM-based RFs in terms of precision and standard deviation, which are used to evaluate the effectiveness and robustness of a RF algorithm, respectively.
|Additional Information:||This is an exact copy of a paper published in IEEE Transactions on Image Processing (ISSN 1057-7149). This material is posted here with permission of the IEEE. Copyright © 2006 IEEE.|
|Keyword(s) / Subject(s):||content-based image retrieval (CBIR), multitraining SVM (MTSVM), relevance feedback (RF), support vector machine (SVM)|
|School or Research Centre:||Birkbeck Schools and Research Centres > School of Business, Economics & Informatics > Computer Science and Information Systems|
|Depositing User:||Sandra Plummer|
|Date Deposited:||30 Jan 2007|
|Last Modified:||17 Apr 2013 12:33|
Archive Staff Only (login required)