원문정보
초록
영어
Compressed sensing is a new signal sampling theory that fully makes use of signal’s sparsity or compressibility. The theory shows that, the acquisition of a small amount of the sparse or compressible signal value can be used for exact signal reconstruction. Based on the study and summarization of the existing reconstruction algorithms, this paper proposes a novel blocking variable step size forward-backward pursuit (BVSSFBP). This paper proposed variable step size forward-backward pursuit algorithm by introducing the concept of sparse phase and variable step size to deal with different situations. The algorithm also divides two-dimensional image into blocks, in order to reduce the scale of observation matrix during single processing, reduce the single processing speed and the overall running time. Experimental results show BVSSFBP algorithm can obtain better reconstructed image quality.
목차
1. Introduction
2. Compressed Sensing and Reconstruction Algorithm
3. VSFBP Algorithm
4. BVSSFBP Algorithm
5. Experiments and Analysis
5.1 The Selection of Block Size
5.2 The Selection of Sampling Rate
5.3 Equalization Operation
6. Conclusion
References