2.利用稀疏恢复算法得到稀疏矩阵，结合稀疏表示的相关知识以及得到的稀疏

2. Use the sparse recovery algorithm to obtain the sparse matrix, and combine the relevant knowledge of the sparse representation and the obtained sparse matrix to obtain a high-resolution image. <br>3. Perform numerical simulation based on existing theoretical knowledge. Finally, the method studied in this paper is compared with the interpolation method, and the respective peak signal-to-noise ratio (PSNR) values ​​are calculated, and finally a corresponding summary is made. <br>The experimental results show that this paper achieves the super-resolution enhancement of the original low-resolution image. Compared with the traditional super-resolution algorithm, the super-resolution method based on sparse representation is more advantageous. The results of over-scores in this article are still insufficient. The main reason is that a lot of information has been lost after the original high-resolution image is degraded. This includes a lot of details, so it will result in poor quality of the images after over-score.

2. The sparse matrix is obtained by sparse recovery algorithm, combined with the relevant knowledge of sparse representation and the resulting sparse matrix to obtain high-resolution image.<br>3. Numerical simulation is carried out according to the existing theoretical knowledge. Finally, the method studied in this paper is compared with the interpolation method, and the respective peak signal-to-noise ratio (PSNR) values are calculated, and finally the corresponding summary is made.<br>The experimental results show that the super-resolution enhancement of the original low-resolution image is realized, which is more advantageous than the ultra-resolution method based on sparse representation compared to the traditional super-resolution algorithm. The results of the super-score in this paper are still insufficient, the main reason is that a lot of information has been lost after the original high-resolution image quality, which includes a lot of details, so that the quality of the image after the super-score is not very good.

2. Sparse matrix is obtained by sparse recovery algorithm, and high-resolution image is obtained by combining the knowledge of sparse representation and sparse matrix.<br>3. Carry out numerical simulation according to the existing theoretical knowledge. At last, we compare the method with interpolation method, and calculate the PSNR value of each method. Finally, we make a summary.<br>The experimental results show that this paper realizes the super-resolution enhancement of the original low-resolution image. Compared with the traditional super-resolution algorithm, the super-resolution method based on sparse representation has more advantages. The main reason is that a lot of information has been lost after the original high-resolution image is degraded, which includes a lot of details, so it will lead to the poor quality of the image.