Fourier single-pixel imaging based on sampling prediction from intermediate frequencies

Abstract

The imaging quality of Fourier single pixel imaging (FSI) is determined by the number of samples, therefore higher image quality requires more sampling times. Common low-frequency sampling methods compromise high-frequency signals to reduce the number of samples, but this will reduce the resolution of the reconstructed image. The recent adaptive sampling methods can reconstruct high-quality images with low sampling ratio, but the calculation of sampling trajectories is a time-consuming process. To improve imaging efficiency, we propose a fast sampling method based on intermediate frequency prediction for FSI. This method utilizes the continuity and directionality of important frequency distributions in the Fourier spectrum, according to which regions of important high-frequency components can be quickly predicted by firstly identifying important frequency components on the intermediate frequency ring. The simulation and experiment results demonstrated our method is 9 times faster than existing adaptive sampling methods in predicting sampling trajectories while maintaining similar image reconstruction quality for an image of 256 × 256 pixels under 5% sampling ratio. In addition, our method can efficiently sample important spectral components of images that has different frequency distributions, which proves that this method has the potential for wide applications.