Further results on dissimilarity spaces for hyperspectral images RF-CBIR

• A RF method for hyperspectral CBIR is proposed based on dissimilarity spaces.
• Dissimilarities are defined using spectral unmixing based dissimilarities.
• Dissimilarity are defined using the normalized dictionary distance.
• Offline and online prototype selection methods are tested.
• Validation is provided over an hyperspectral dataset with great success.

Content-Based Image Retrieval (CBIR) systems are powerful search tools in image databases that have been little applied to hyperspectral images. Relevance feedback (RF) is an iterative process that uses machine learning techniques and user’s feedback to improve the CBIR systems performance. We pursued to expand previous research in hyperspectral CBIR systems built on dissimilarity functions defined either on spectral and spatial features extracted by spectral unmixing techniques, or on dictionaries extracted by dictionary-based compressors. These dissimilarity functions were not suitable for direct application in common machine learning techniques. We propose to use a RF general approach based on dissimilarity spaces which is more appropriate for the application of machine learning algorithms to the hyperspectral RF-CBIR. We validate the proposed RF method for hyperspectral CBIR systems over a real hyperspectral dataset.