Abstract | ||
---|---|---|
Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.jvcir.2013.10.006 | J. Visual Communication and Image Representation |
Keywords | Field | DocType |
context-aware feature extraction,local feature extractor,image content,context-aware feature,robust image representation,robust representation,complementary feature,local image feature,local feature,image context,complementarity,information theory | Complementarity (molecular biology),Feature detection (computer vision),Image representation,Artificial intelligence,Information theory,Computer vision,Pattern recognition,Feature (computer vision),Feature extraction,Extractor,Completeness (statistics),Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
25 | 2 | 1047-3203 |
Citations | PageRank | References |
3 | 0.40 | 30 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
P. Martins | 1 | 15 | 2.25 |
Paulo Carvalho | 2 | 250 | 47.68 |
C. Gatta | 3 | 521 | 37.03 |