Using the SpectraCube to Build a Multispectral Image Database

Multispectral image capture, unlike traditional RGB imaging, records the colour signals in a scene. Most available devices are either filter-wheel multiple exposure systems or point-measuring diffraction grating based devices. In this article we introduce a 2D matrix, full spectral, single exposure capture system – the Applied Spectral Imaging SpectraCube – which determines multispectral images, building on on the principle of interferometry. We explain the theory of operation of the SpectraCube, show characterisation results and present an initial multispectral database of indoor images. This step is not trivial. Often there are significant errors in the spectra captured by the SpectraCube. However, these errors are surprisingly regular and can be corrected. The images were captured at a high spectral resolution, comparable to spectroradiometers, yet at an exposure significantly shorter than that of filter-wheel based systems.