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:祝毅鸣[1] ZHU Yi-ming(Sias International University,Zhengzhou University,Xinzheng Henan 451150,China)
机构地区:[1]郑州大学西亚斯国际学院,河南新郑451150
出 处:《计算机仿真》2021年第1期486-490,共5页Computer Simulation
摘 要:角点是展现局部图像特征的关键要素,但传统图像角点特征取证检测方法精度低,无法有效的解决角点特征图像中模糊、缺失等问题。为此,对面向图像角点特征取证的人工智能检测进行研究。通过在不同干扰情况下对图像做简化处理,完成特征取证。采用掩模平滑方法将提取出图像角点做增强处理,最后利用人工智能中链码和与差算法对图像做检测。结果表明,面向图像角点特征取证的人工智能检测精准度较高,可以有删除假图像角点,使用结果更贴近真实情况,具有较高鲁棒性。Corner point is the key element to show local image feature.The traditional method cannot effectively solve the problems of blur and missing in corner feature image.In this article,a method of artificial intelligence detection based on image corner feature forensics was researched.By simplifying the image under different interference conditions,we completed the feature forensics.Then,we used the mask smoothing method to enhance the extracted corner points of image.Finally,we used the chain code and the difference algorithm in artificial intelligence to detect the image.The results show that the accuracy of artificial intelligence detection for image corner feature forensics is high,and the false image corner can be deleted,so that the results are close to the real situation.Therefore,it has high robustness.
关 键 词:图像角点 角点特征取证 人工智能检测 检测准确率 增强处理
分 类 号:TN911[电子电信—通信与信息系统]
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:216.73.216.28