Separating Reflective and Fluorescent Components Using High Frequency Illumination in the Spectral Domain

Deep Blind Hyperspectral Image Super-Resolution

The production of a high spatial resolution (HR) hyperspectral image (HSI) through the fusion of a low spatial resolution (LR) HSI with an HR multispectral image (MSI) has underpinned much of the recent progress in HSI super-resolution. The premise of these signs of progress is that both the degeneration from the HR HSI to LR HSI in the spatial domain and the degeneration from the HR HSI to HR MSI in the spectral domain are assumed to be known in advance. However, such a premise is difficult to achieve in practice. To address this problem, we propose to incorporate degeneration estimation into HSI super-resolution and present an unsupervised deep framework for "blind" HSIs super-resolution where the degenerations in both domains are unknown. In this framework, we model the latent HR HSI and the unknown degenerations with deep network structures to regularize them instead of using handcrafted (or shallow) priors. Specifically, we generate the latent HR HSI with an image-specific generator network and structure the degenerations in spatial and spectral domains through a convolution layer and a fully connected layer, respectively. By doing this, the proposed framework can be formulated as an end-to-end deep network learning problem, which is purely supervised by those two input images (i.e., LR HSI and HR MSI) and can be effectively solved by the backpropagation algorithm. Experiments on both natural scene and remote sensing HSI data sets show the superior performance of the proposed method in coping with unknown degeneration either in the spatial domain, spectral domain, or even both of them.

Estimation of fluorescent Donaldson matrices using a spectral imaging system

The present paper proposes a method to estimate the bispectral Donaldson matrices of fluorescent objects in a scene with a spectral imaging system. Multiple ordinary light sources with continuous spectral-power distributions are projected sequentially onto object surfaces without controlling the spectral shape of the illumination source. The estimation problem of the Donaldson matrices is solved as an optimization problem, where the residual error of observations by the spectral imaging system is minimized. The reflection, emission, and excitation spectral functions are estimated at each wavelength without using a basis function approximation. To improve the estimation efficiency, the output visible range is segmented into two types of wavelength ranges: one for only reflection and another for both reflection and emission. An iterative algorithm is then developed based on the wavelength segmentation and the physical excitation model. The usefulness of the proposed method is examined in experiments using different fluorescent objects and illuminants. We show the estimation accuracy of the Donaldson matrices, discuss the effective selection of illuminants, and demonstrate an application to spectral analysis and reconstruction of a fluorescent image.