期刊文献+

MIF-CNNIF:一种基于CNN的交叉特征的多分类图像数据框架 被引量:1

MIF-CNNIF:A Multi-classification Image Data Framework Based on CNN with Intersect Features
在线阅读 下载PDF
导出
摘要 近年来,图像多分类任务和深度学习受到越来越多学者的重视,基于卷积神经网络(Convolutional Neural Network,CNN)的多分类图像数据框架也得到了广泛应用。传统的基于卷积神经网络的多分类图像数据学习(MIF-CNN)普遍存在图像处理复杂、特征维数大、时间复杂度高等问题。针对这一问题,提出了一种基于CNN的交叉特征的多分类图像数据框架(MIFCNNIF)。MIF-CNNIF是一种基于多种特征选择算法得到相交特征并以此交叉特征代替原特征集处理图像多分类任务的框架。在10个多类图像数据集上进行了丰富的对比实验,结果验证了MIF-CNNIF的有效性。MIF-CNNIF的贡献在于:1)使用预先训练好的CNN模型,避免了设置过多参数;2)与MIF-CNN相比,有效降低了特征维度和时间复杂度;3)具有比MIF-CNN更好的平均分类准确率;4)在多分类图像数据集上成功验证了组合特征算法的有效性。 In recent years,image multi-classification task and deep learning have received increasingly attentions,and multi-classification image data framework based on convolutional neural network(MIF-CNN)has also been widely used.Traditional CNNbased multi-class image data learning generally has a problem that the image processing is complicated,the feature dimensions are large,and the time complexity is high.To solve this problem,this paper proposes a multi-classification image data framework based on CNN with intersect features(MIF-CNNIF).MIF-CNNIF is a framework for performing multi-classification tasks based on intersect features obtained by multiple feature selection algorithms.Through extensive comparative experiments on 10multiclass image data sets,the results validate the effectiveness of MIF-CNNIF.The contributions of MIF-CNNIF are that,1)it avoids the problem of setting too many parameters with the usage of pre-trained CNN models;2)it keeps features dimension and time cost after comparing with MIF-CNN;3)it has a better average recognition accuracy than MIF-CNN;4)the effectiveness of combined feature algorithms is verified on multi-class image data sets.
作者 王盼红 朱昌明 WANG Pan-hong;ZHU Chang-ming(College of Information Engineering,Shanghai Maritime University,Shanghai 201306,China)
出处 《计算机科学》 CSCD 北大核心 2022年第S02期502-509,共8页 Computer Science
基金 国家自然科学基金(62276164,61602296) 上海市"科技创新行动计划"自然科学基金项目(22ZR1427000) 晨光计划(18CG54) 中国博士后科学基金(2019M651576)
关键词 卷积神经网络 特征选择 交叉特征 图像多分类 组合特征 Convolutional neural network Feature selection Intersect features Image multi-class Combine feature
作者简介 通信作者:朱昌明,cmzhu@shmtu.edu.cn,born in 1988,Ph.D.candidate at the East China University of Science and Technology.He is an associate professor in Shanghai Maritime University.His research interest covers image processing and multi-view learning;WANG Pan-hong,born in 1998,postgraduate.Her main research interests include machine learning,online features selection.
  • 相关文献

参考文献3

二级参考文献29

共引文献21

同被引文献4

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部