基于双层混合字典学习的图像超分辨率复原

提出了一种新的字典学习法用于图像的超分辨率复原,即双层混合字典。其中,第一层字典采用半耦合字典,确保了复原过程的灵活性和准确性,并结合稀疏表示算法得到第一层复原图像;为了不影响算法的整体运算速度,第二层字典采用分类字典,并利用原始图像与第一层复原图像的差值作为高分辨率样本,以便能恢复更多的高频细节。实验结果表明,本算法与传统的基于单一字典的图像超分辨率算法相比,无论是在视觉效果上,还是峰值信噪比(PSNR)指标,都取得了更为理想的效果,有效地改善了降质图像的质量。

Image super-resolution recovery based on dual-mixed dictionary learning

A new method of dictionary learning is proposed for image super-resolution, which is named dual-mixed dictionary. Among them, the first layer dictionary uses semi-coupled dictionary, which ensures the flexibility and accuracy of the recovery process, and combines with sparse representation algorithm to get the first layer of the restored image. In order not to affect the overall computing speed, the second layer dictionary adopts classification dictionary, and uses the difference between the original image and the first layer of the restored image as the high resolution sample to restore more high frequency details. The experiment results show that the proposed algorithm has remarkable improvement in visual quality and peak signal-to-noise ratio in comparison with the traditional image super-resolution algorithm based on single dictionary, effectively improves the quality of the images.