摘要
为了提高摄像机成像质量和图像清晰度,提出了一种基于多通道视觉注意力的模糊图像质量复原算法。在多通道视觉注意力机制的基础上构建了编码网络,将模糊图像输入到编码网络中,对图像展开复原处理;同时,在复原处理过程中引入振铃检测,消除复原后图像中存在的振铃区域,提高复原图像的质量和清晰度。实验结果表明,本文算法的去振铃现象效果更好、图像复原后的质量更高、应用效率更理想。
In order to improve the imaging quality of the camera and improve the image definition,a fuzzy image quality restoration algorithm based on multi-channel visual attention was proposed.Based on the multi-channel visual attention mechanism,the coding network was constructed.The blurred image is input into the coding network,and the image was restored.At the same time,the ringing detection was introduced in the restoration process to eliminate the ringing area in the restored image and improve the quality and clarity of the restored image.The experimental results show that the proposed algorithm has better effect of de ringing phenomenon,high quality after image restoration,and better application efficiency.
作者
陈烽
王浩
CHEN Feng;WANG Hao(College of Information Engineering,Xizang Minzu University,Xianyang 712082,China)
出处
《吉林大学学报（工学版）》
EI
CAS
CSCD
北大核心
2023年第9期2626-2631,共6页
Journal of Jilin University:Engineering and Technology Edition
基金
国家自然科学基金项目(62062061)。
关键词
多通道视觉注意力
模糊图像
振铃效应
编码网络
图像质量复原
multi-channel visual attention
blurred image
ringing effect
coding network
image quality restoration
