欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
如何利用更多的图像先验知识来提高图像的重构质量是压缩感知的一个关键问题.本文将综合稀疏模型与近几年提出的Cosparse解析模型结合,利用图像在综合字典和解析字典下的稀疏性提出了一种融合两种稀疏先验的图像重构算法,并利用交替方向乘子法（ADMM）求解对应的复杂优化问题.为进一步提高算法性能,该算法还充分利用了图像中任意位置图像块的稀疏性.实验结果表明,本文算法能有效提高图像重构质量.
英文摘要：
How to improve the reconstructed image quality using more prior know ledge of the image is still a crucial issue of compressed sensing. In this paper,w e combine the synthesis sparse model and the cosparse analysis model proposed in recent years,and propose a novel reconstruction algorithm based on the sparsity of the image over a synthesis dictionary and an analysis dictionary. M oreover,alternating direction method of multipliers（ ADM M） is exploited to solve the corresponding complicated optimization problem. To further improve the performance,the sparsity of patches in any position of the image is utilized by the proposed algorithm. The experimental results show that our algorithm can effectively improve the quality of image reconstruction.
同期刊论文项目
同项目期刊论文
Polar angle detection and image combination based leukocyte segmentation for overlapping cell images
Global stability analysis in Cohen–Grossberg neural networks with delays and inverse H?lder neuron a
期刊信息
位置：