改进的暗通道运动图像盲复原方法  

An improved blind restoration method for motion images in dark channels

作　　者：吴清平 WU Qingping(School of Information Management,Minnan University of Science and Technology,Shishi 362700,China)

机构地区：[1]闽南理工学院信息管理学院,福建石狮362700

出　　处：《山东理工大学学报（自然科学版）》2023年第5期68-73,共6页Journal of Shandong University of Technology:Natural Science Edition

基　　金：福建省中青年教师教育科研项目(JAT210515)。

摘　　要：盲复原方法对于解决现实中图像运动模糊问题具有实用性,而目前运动图像盲复原算法普遍存在图像局部细节丢失、模糊核估值不够准确、复原图像存在噪声与振铃效应的问题。对此,提出了一种在多层交替模糊核框架下的分数阶暗通道点扩展函数估计模型,引入分数阶暗通道先验,在多尺度迭代框架下获取更精确的模糊核估值,降低模糊核估计时图像噪点的干扰,实现模糊图像较高质量的复原。通过实验客观评价指标与主观人眼视觉验证盲复原方法的有效性。Blind restoration methods are practical for solving realistic image motion blur problems.The current motion image blind restoration algorithm generally suffers from loss of local details,lack of accurate blur kernel valuation,and noise and ringing effects in the recovered image.A fractional-order dark channel point expansion function estimation model which introduces a fractional-order dark channel prior in a multilayer alternating fuzzy kernel framework is put forward,in order to obtain more accurate fuzzy kernel valuation in a multiscale iterative framework,reduce the interference of image noise during fuzzy kernel estimation,and achieve a higher quality recovery of fuzzy images.The effectiveness of the blind recovery method is verified through experimental objective evaluation indexes and subjective human eye vision.

关 键 词：盲复原 分数阶暗通道 混合约束 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]