检索结果-南通市图书馆

Clothing identification via deep learning:forensic applications

Forensic Sciences Research 2018年第3期3卷 219-229页

作者： Marianna Bedeli Zeno Geradts erwin van eijk University of Amsterdam AmsterdamThe Netherlands Netherlands Forensic Institute(NFI) Den HagueThe Netherlands

Attribute-based identification systems are essential for forensic investigations because they help in identifying *** item such as clothing is a visual attribute because it can usually be used to describe *** method proposed in this article aims to identify people based on the visual information derived from their *** learning is used to train the computer to classify images based on clothing *** first demonstrate clothing classification using a large scale dataset,where the proposed model performs relatively ***,we use clothing classification on a dataset containing popular logos and famous brand *** results show that the model correctly classifies most of the test images with a success rate that is higher than 70%.Finally,we evaluate clothing classification using footage from surveillance *** system performs well on this dataset,labelling 70%of the test images correctly.

关键词： Forensic sciences digital forensic clothing classification attribute identification systems deep learning large scale dataset surveillance camera

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Camera recognition with deep learning

引用

Forensic Sciences Research 2018年第3期3卷 210-218页

作者： Eleni Athanasiadou Zeno Geradts erwin van eijk Department of Forensic Science University of Amsterdam AmsterdamThe Netherlands Netherlands Forensic Institute Den Haag Den HaagThe Netherlands

In this paper,camera recognition with the use of deep learning technique is *** identify the various cameras,their characteristic photo-response non-uniformity(PRNU)noise pattern was *** forensic science,it is important,especially for child pornography cases,to link a photo or a set of photos to a specific *** learning is a sub-field of machine learning which trains the computer as a human brain to recognize similarities and differences by scanning it,in order to identify an *** innovation of this research is the use of PRNU noise patterns and a deep learning technique in order to achieve camera *** this paper,AlexNet was modified producing an improved training procedure with high maximum accuracy of 80%–90%.DIGITS showed to have identified correctly six cameras out of 10 with a success rate higher than 75%in the ***,many of the cameras were falsely identified indicating a fault occurring during the procedure.A possible explanation for this is that the PRNU signal is based on the quality of the sensor and the artefacts introduced during the production process of the *** manufacturers may use the same or similar imaging sensors,which could result in similar PRNU noise *** an attempt to form a database which contained different cameras of the same model as different categories,the accuracy rate was *** provided further proof of the limitations of this technique,since PRNU is stochastic in nature and should be able to distinguish between different cameras from the same ***,this study showed that current convolutional neural networks(CNNs)cannot achieve individualization with PRNU ***,the paper provided material for further research.

关键词： Forensic sciences camera identification clustering individualization deep learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：