Design of optimal illumination patterns in single-pixel imaging using image dictionaries
share
Single-pixel imaging (SPI) has a major drawback that the huge number of sequential illuminations for capturing one single image requires long acquisition time and high cost. Basis illumination patterns such as sinusoidal patterns in Fourier transform and Hadamard patterns are employed to enhance the imaging efficiency. The basis illumination patterns can achieve much better efficiency than random intensity illumination patterns but the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying object images. In this work, we propose a novel scheme to design the illumination patterns adaptively when SPI is applied in a specific and pre-known imaging scenario. Exemplar training images belonging to the target specific category of object images are collected and an image dictionary is constructed in advance. Then the optimized illumination patterns are designed by extracting the common image features from the image dictionary using principal component analysis. Simulation results reveal that our proposed scheme outperforms conventional Fourier single-pixel imaging in terms of imaging efficiency.
READ FULL TEXT