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:连自锋[1,2] 景晓军[1,2] 孙松林[1,2] 黄海[2] LIAN Zi-feng JING Xiao-jun SUN Song-lin HUANG Hai(School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China Key Laboratory of Trustworthy Distributed Computing and Service, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China)
机构地区:[1]北京邮电大学信息与通信工程学院,北京100876 [2]北京邮电大学可信分布式计算与服务教育部重点实验室,北京100876
出 处:《北京邮电大学学报》2016年第5期1-5,32,共6页Journal of Beijing University of Posts and Telecommunications
基 金:国家自然科学基金项目(61143008;61471066);国家高技术研究发展计划(863计划)项目(2011AA01A204)
摘 要:卷积神经网络模型要求训练图像与测试图像在空间尺度上一致.为弱化这一限制,对卷积层特征提取器进行多尺度改进,提出了一种尺度不变卷积神经网络模型,以自动适应输入图像在平面空间上的尺度变化.同时,将多层Maxout网络嵌入新模型中,以进一步提高特征提取能力,提高图像识别与分类的准确性.实验测试结果表明,该模型提高了传统卷积神经网络模型的尺度不变性和分类精度.Convolution neural network models require the consistency of spatial scales between training images and testing images. In order to alleviate this restriction,a scale invariant convolution neural network model with multi-scale feature extractor was proposed,which can adapt to the in-plane scale change of input images. Meanwhile,multi-layer Maxout networks are nested into the model in order to improve the ability of feature extraction,so as to improve the accuracy of image recognition and classification. Experiments show that the new model improves the scale invariance and classification accuracy of traditional convolution neural networks.
分 类 号:TN911.22[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:216.73.216.222