Files in this item

FilesDescriptionFormat

application/vnd.openxmlformats-officedocument.wordprocessingml.document

application/vnd.openxmlformats-officedocument.wordprocessingml.documentZhang_Lu_Poster.docx (343kB)
(no description provided)Microsoft Word 2007

Description

Title:Biomedical compound figure detection using deep convolutional neural network
Author(s):Zhang, Guobiao; Lu, Wei
Subject(s):Compound image detection
Biomedical images
Deep learning
VGG16
ImageCLEFmed
Abstract:Scientific figures contain significant amounts of information but present different challenges relative to image retrieval. One such challenge is compound figures or images made up of two or more subfigures. A deep convolutional neural network model is proposed for compound figure detection (CFD) in the biomedical article domain. Our architecture is inspired by the success of VGG16 and uses large-size convolution kernel in first layer. The proposed model obtained a best test accuracy of 97.08% outperforming traditional hand-crafted and other deep learning representations on the ImageCLEF2016 CFD subtask datasets.
Issue Date:2019-03-15
Publisher:iSchools
Series/Report:iConference 2019 Proceedings
Genre:Conference Poster
Type:Text
Language:English
URI:http://hdl.handle.net/2142/103376
DOI:https://doi.org/10.21900/iconf.2019.103376
Rights Information:Copyright 2019 Guobiao Zhang and Wei Lu
Date Available in IDEALS:2019-03-22


This item appears in the following Collection(s)

Item Statistics