检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:田洋川 徐慧娴 陈明举 李天宇 吕旋 石浩德 TIAN Yangchuan;XU Huixian;CHEN Mingju;LI Tianyu;LV Xuan;SHI Haode(Sichuan University of Science and Engineering,Artificial Intelligence Key Laboratory of Sichuan Province,Yibin 644000,China;School of Automation and Information Engineering,Sichuan University of Science&Engineering,Yibin 644000,China;Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things,Yibin 644000,China)
机构地区:[1]四川轻化工大学人工智能四川省重点实验室,四川宜宾644000 [2]四川轻化工大学自动化与信息工程学院,四川宜宾644000 [3]四川轻化工大学企业信息化与物联网测控技术四川省高校重点实验室,四川宜宾644000
出 处:《传感器与微系统》2023年第12期130-133,共4页Transducer and Microsystem Technologies
基 金:企业信息化与物联网测控技术四川省高校重点实验室开放基金资助项目(2021WYY01);人工智能四川省重点实验室(2020RZY02);四川轻化工大学研究生课程建设项目(KA202030);四川省科技厅项目(2020JDJQ0075,2020YFSY0027)。
摘 要:为了提高多聚焦图像融合的效果,提出了一种基于引导滤波和图像抠图的多聚焦图像融合方法。首先,通过中值滤波器对源图像进行重复模糊处理,并使用差分算子获得图像的梯度信息。然后,使用引导滤波对梯度图像进行优化处理并获得初始决策图。为了获得更准确的决策图,对初始决策图进行膨胀和腐蚀操作,生成图像抠图中的三值图,并把三值图和原始图像送入图像抠图算法中进行优化,得到精确决策图。最终,根据最终决策图和源图像得到融合结果。实验结果表明:提出的模型和7种先进的方法相比,无论在主观上还是客观上都取得更好的融合性能。In order to improve effect of multi-focus image fusion,a multi-focus image fusion method based on guided filtering and image matting is proposed.Firstly,the source image is repeatedly fuzzy processing by median filter,and the gradient information of the image is obtained using the difference operator.Then,guided filtering is used to optimize and process the gradient image and obtain the initial decision diagram,In order to obtain a more accurate decision diagram,expansion and erosion operations are performed on the initial decision diagram to generate a ternary diagram in the image matting,and the ternary diagram and the original image are sent to the image matting algorithm for optimization to obtain an accurate decision diagram,Finally,the fusion result is obtained according to the final decision diagram and the source image.Experimental results show that compared with 7 advanced methods,the proposed model achieves better fusion performance in subjective and objective evaluation.
分 类 号:TP391.7[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.49