基于稀疏K-SVD的单幅图像超分辨率重建算法

图像的超分辨率重建技术可以提升图像质量，改善图像视觉效果，在现实中具有很高的实用价值。针对基于K-SVD的超分辨率重建算法的不足，本文提出一种基于稀疏K-SVD的单幅图像超分辨率重建算法。首先，采用稀疏K-SVD方法进行训练获得高低分辨率字典对，以待重建的低分辨率图像及其降采样作为字典训练的样本，提高了字典和待重建的低分辨率图像的相关性；然后，采用逐级放大的思想进行重建；最后，利用非局部均值的方法，进一步提高重建效果。实验表明，与基于K-SVD的超分辨率重建算法相比，本文算法重建图像的峰值信噪比平均提高了0.6dB左右。重建图像在视觉效果上，也有一定程度的提升。

Single image super-resolution reconstruction based on sparse K-SVD

Super-resolution reconstruction can enhance the image quality and improve the visual perception, which plays an important role in the real world. For the problems in the image super-resolution method based on K-SVD, a new method based on sparse K-SVD is proposed and used for license plate images reconstruction. Firstly, the low-resolution (LR) license plate images and their downsampling versions are used as samples to train dictionary, which improves the relativity between the dictionary and the LR license plate image. And The sparse K-SVD method is used for dictionary training to obtain a pair of dictionaries. Then, a gradual magnification scheme is used for reconstruction. Finally, the non-local means is exploited to further improve the reconstruction performance. Experimental results on license plate images show that the PSNR is improved by nearly 0.6 dB compared to the image super-resolution method based on K-SVD, and our method also has a better visual improvement to certain extent.