Name
Abstract | ||
|---|---|---|
The learning of image representation is always the most important problem in computer vision community. In this paper, we propose a novel image representation method by learning and using kernel classifiers. We firstly train classifiers using the one-against-all rule, then use them classify the candidate images, and finally using the classification responses as the new representations. The Euclidean distance between the classification response vectors are used as the new similarity measure. The experimental results from a large scale image database show that the proposed algorithm can outperform the original feature on image retrieval problem. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICTAI.2014.131 | ICTAI |
Keywords | Field | DocType |
image representation,image representation learning,large scale image database,kernel classifier training,learning (artificial intelligence),euclidean distance,visual databases,kernel classification,image classification,image retrieval,image retrieval problem,computer vision,one-against-all rule,image classification response vectors,similarity measure,image retrieval, image representation, kernel classification,computer vision community | Automatic image annotation,Feature detection (computer vision),Radial basis function kernel,U-matrix,Pattern recognition,Computer science,Pyramid (image processing),Image retrieval,Scale space,Artificial intelligence,Contextual image classification,Machine learning | Conference |
ISSN | Citations | PageRank |
1082-3409 | 78 | 1.87 |
References | Authors | |
28 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haoxiang Wang | 1 | 276 | 15.25 |
| Jingbin Wang | 2 | 472 | 20.56 |