中文摘要：

针对基于稀疏表示的传统图像复原方法无法准确恢复图像小尺度细节的不足,提出了一种结合稀疏表示与匹配梯度分布的图像复原方法。首先在稀疏表示图像复原模型的基础上,利用参数化的超拉普拉斯分布估计原始图像的梯度分布;然后,通过对图像的梯度分布进行全局约束,利用梯度直方图匹配操作匹配图像梯度分布,使复原图像的梯度分布尽可能接近原始图像。仿真实验结果表明,本文算法能够取得较优的复原效果,并且能以较高精度复原图像的细节信息。

英文摘要：

An image often contains different levels of degradation. In order to obtain a higher quality image from the degraded image, different kinds of restoration methods have been proposed. Since the sparse characteristics of natural images have been well revealed in the past several decades,the sparse represen ration based methods are considered as the most promising algorithms. However, the present image res toration methods based on sparse representation cannot accurately represent small scale details of recon structed images. To overcome this drawback, a new image restoration method which combines sparse representation and matching gradient distribution is proposed. To improve the performance of the traditional image restoration model based on sparse representation, the proposed algorithm utilizes a parameterized hyper-Laplace model to estimate the gradient distribution of the original image. Then a global constraint is applied on the gradient distribution of images, and the histogram specification operation is performed to match the gradient distribution. Thus the gradient distribution of the reconstructed image is similar to that of the original image. Numerical experimental results indicate that the proposed algorithm has good recovery performance, and can represent the image details with high accuracy.