Context-aware features and robust image representations

• No a priori assumption is made on the type of structure to be extracted.
• Suitable for robust image representation.
• Different instances of the method can be created.
• In some cases, context-aware features can be complemented with strictly local features without inducing redundancy.
• Repeatability scores are comparable to state-of-the-art methods.

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.