Toward Content-Based Hyperspectral Remote Sensing Image Retrieval (CB-HRSIR): A Preliminary Study Based on Spectral Sensitivity Functions

Abstract

With the emergence of huge volumes of high-resolution Hyperspectral Images (HSI)produced by different types of imaging sensors, analyzing and retrieving these images requireeffective image description and quantification techniques. Compared to remote sensing RGB images,HSI data contain hundreds of spectral bands (varying from the visible to the infrared ranges) allowingprofile materials and organisms that only hyperspectral sensors can provide. In this article, we studythe importance of spectral sensitivity functions in constructing discriminative representation ofhyperspectral images. The main goal of such representation is to improve image content recognitionby focusing the processing on only the most relevant spectral channels. The underlying hypothesisis that for a given category, the content of each image is better extracted through a specific set ofspectral sensitivity functions. Those spectral sensitivity functions are evaluated in a Content-BasedImage Retrieval (CBIR) framework. In this work, we propose a new HSI dataset for the remotesensing community, specifically designed for Hyperspectral remote sensing retrieval and classification.Exhaustive experiments have been conducted on this dataset and on a literature dataset. Obtainedretrieval results prove that the physical measurements and optical properties of the scene containedin the HSI contribute in an accurate image content description than the information provided by theRGB image presentation.