Blind infrared spectroscopic data restoration with the similarity of multi-scales regularization

Band overlap and random noise exist widely when the spectra are captured using an infrared spectrometer, especially when the problems of instrument aging has become more and more serious recently. In this paper, via introducing the similarity of multiscales, a blind spectral deconvolution method is proposed. Considering similarity of the latent spectrum between different scales, it is used as a prior to constrain the estimated latent spectrum similar to pre-scale to reduce artifacts which is produced from deconvolution. Experiments indicate that the proposed method is able to obtain better performance than the state-of-the-art methods, and obtain satisfying deconvolution results with fewer artifacts. The recovered infrared spectra can easily extract the spectral features and recognize the unknown objects.