自适应稀疏约束图像超分辨力重建方法

Adaptive Sparse Constraint Image Super-Resolution Reconstruction Method

简要介绍了基于稀疏字典约束的超分辨力重建算法,提出了具有低复杂度的基于K均值聚类的自适应稀疏约束图像超分辨力重建算法。所提算法从两个方面降低其计算复杂度:分类训练字典,对图像块归类重建,降低每个图像块所用字典的大小;对图像块的特征进行分析,自适应地选择重建方法。实验结果表明,提出的快速重建方法在重建质量与原算法相当的前提下,可以较大程度地降低重建时间。

In this paper, sparse dictionary constraint based image SR method is briefly introduced and an adaptive fast reconstruction method based on the K-Means clustering is presented to reduce the reconstruction computation complexity. The proposed SR reduces its complexity from two aspects. First, the dictionary size for each image patch in the learning process is reduced by classifying the sampled raw patches in the dictionary training process. Second, the reconstruction algorithm according to the features existed in each patch is adaptively selected. Experimental results show that the proposed fast reconstruction method takes much less time while generating images equivalent to the original algorithm.