HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

Fine-tuning deep convolutional neural networks for distinguishing illustrations from photographs

Creative Commons License

Files in This Item:
manuscript_eswa0820.pdf935.26 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/72243

Title: Fine-tuning deep convolutional neural networks for distinguishing illustrations from photographs
Authors: Gando, Gota Browse this author
Yamada, Taiga Browse this author
Sato, Haruhiko Browse this author →KAKEN DB
Oyama, Satoshi Browse this author →KAKEN DB
Kurihara, Masahito Browse this author →KAKEN DB
Keywords: Aggregation systems
Machine learning
Deep learning
Illustrations
Issue Date: 30-Dec-2016
Publisher: Elsevier
Journal Title: Expert Systems with Applications
Volume: 66
Start Page: 295
End Page: 301
Publisher DOI: 10.1016/j.eswa.2016.08.057
Abstract: Systems for aggregating illustrations require a function for automatically distinguishing illustrations from photographs as they crawl the network to collect images. A previous attempt to implement this functionality by designing basic features that were deemed useful for classification achieved an accuracy of only about 58%. On the other hand, deep neural networks had been successful in computer vision tasks, and convolutional neural networks (CNNs) had performed good at extracting such useful image features automatically. We evaluated alternative methods to implement this classification functionality with focus on deep neural networks. As the result of experiments, the method that fine-tuned deep convolutional neural network (DCNN) acquired 96.8% accuracy, outperforming the other models including the custom CNN models that were trained from scratch. We conclude that DCNN with fine-tuning is the best method for implementing a function for automatically distinguishing illustrations from photographs.
Rights: © 2016, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
http://creativecommons.org/licenses/by-nc-nd/4.0/
Type: article (author version)
URI: http://hdl.handle.net/2115/72243
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 小山 聡

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

Feedback - Hokkaido University