Research On Image Recovery Method Based On Compressed Sensing

Compressive sensing is a novel sampling theory under the condition that the signal is sparse or compressible. in this case, the small amount of signal values can be reconstructed accurately when the signal is sparse or compressible. The theory breaks though the traditional Nyquist sampling theory, which is a revolutionary way to achieve the data. In this way, we can overcome an amount of problems such as a great number of sampling data, data physical resources wasting and so on. The theory contains three key points:Sparse representation, observation sampling and Signal Recovery. Signal Recovery is the key part of it for the precise reconstruction of the compressed signal and verify the accuracy of the sampling process are of great significance.The key of Signal Recovery is how to get from the perception of compressed data in low-dimensional accurately recover the original high-dimensional data. In the foundation of the deeper research on the existing methods, and mainly research on the following aspects in this paper:(1) Compressed sensing can greatly reduce the value of sampling required, be used for MRI can greatly shorten the scan time and reduce the pain of patient during the scan, the combination of optimization, proposed a reconstruction algorithm is easy to implement, experimental results show that the proposed reconstruction algorithm is better than existing algorithms have significantly improved.(2) In the perception of BCS-SPL, with random structured observation matrix, iterative reconstruction optimized when adding TV idea, put forward a fast and effective natural image reconstruction algorithm. The algorithm can effectively avoid the perception of BCS-SPL generated in the process of blocking effects, and thus the quality and image reconstruction results in better visual effect on the increase.(3) The original image processing algorithms, the image of a transformation, such as discrete cosine transform, wavelet transform, in the transform domain coefficients show some distribution characteristics. We according to the image data in the transform domain sampling distribution characteristics, and select the appropriate reconstruction algorithm, the results of reconstruction have improved.