Double-channel cyclic image deblurring algorithm based on edge features  

基于边缘特征的双通道循环图像去模糊算法

作　　者：LI Jiamin HU Hongping BAI Yanping 李佳敏;胡红萍;白艳萍(中北大学数学学院,山西太原030051)

机构地区：[1]School of Mathematics,North University of China,Taiyuan 030051,China

出　　处：《Journal of Measurement Science and Instrumentation》2025年第1期75-84,共10页测试科学与仪器(英文版)

基　　金：supported in part by Natural Science Research Foundation of Shanxi Province(Nos.20210302123019,20210302124195,20210302124212,20210302123189)。

摘　　要：Photographs taken in daily life often became blurred due to shaking,out-of-focus,changes in depth of field,and movement of photographed objects.Aiming at this problem,a double-channel cyclic image deblurring method based on edge features was proposed.Firstly,image edge gradient operator was introduced as a threshold based on the rule that the maximum value of the image edge gradient will decrease after the blurring process,making the blurred image be divided into two channels:edge channel and non-edge channel.Secondly,a double-channel loop iteration network was designed,where the edge gradient was used in the edge channel to sample the main edge structure and bilateral filtering was used in the non-edge channel to extract the detailed texture feature information.Finally,the feature information extracted from two channels was cyclically iterated to obtain a clear image using the deblurring model with maximum a posteriori probability.The experimental results showed that the image evaluation indexes obtained by the proposed deblurring model were superior to those of other algorithms,and the edge structure and texture details of the image were effectively recovered with better performance.人们拍摄的照片经常由于抖动、失焦、景深变化、拍摄物体运动等问题而变得模糊,针对这一现象,提出了基于边缘特征的双通道循环图像去模糊方法。首先,根据经模糊处理后图像边缘梯度最大值会减小这一规律引入了图像边缘梯度算子,并将其作为阈值将模糊图像来划分为两个通道:边缘通道和非边缘通道。其次,设计了双通道循环迭代网络,在边缘通道上利用边缘梯度对主要边缘结构进行采样,在非边缘通道上利用双边滤波提取细节纹理特征信息。最后,将两个通道提取的特征信息进行循环迭代,利用最大后验概率的去模糊模型得到清晰图像。实验结果表明,所提出的去模糊模型得到的图像评价指标均高于其他算法,有效恢复了图像边缘结构和纹理细节,性能较好。

关 键 词：double-channel loop iteration bilateral filtering image edge gradient maximum a posteriori probability image deblurring 

分 类 号：TN9[电子电信—信息与通信工程]