Further results on dissimilarity spaces for hyperspectral images RF-CBIR

Miguel Angel Veganzones (1, 2) , Mihai Datcu (3) , Manuel Graña (2)

1 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
2 GIC - Grupo de Inteligencia Computacional
3 Photogrammetry and Image Analysis Department

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.

Mots clés: Hyperspectral imaging; CBIR systems; Dissimilarity spaces; Relevance feedback

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Intelligence artificielle [cs.AI]; Recherche d'information [cs.IR]

Miguel Angel Veganzones, Mihai Datcu, Manuel Graña. Further results on dissimilarity spaces for hyperspectral images RF-CBIR. Pattern Recognition Letters, 2013, 34 (14), pp.1659-1668. ⟨10.1016/j.patrec.2013.05.025⟩. ⟨hal-00840863⟩