A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition
We present a saliency-based patch sampling strategy for recognizing artistic media from artwork images using a deep media recognition model, which is composed of several deep convolutional neural network-based recognition modules. The decisions from the individual modules are merged into the final d...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/9/1053 |
id |
doaj-d104f6ffca074252b14d1314f8e7e6ef |
---|---|
record_format |
Article |
spelling |
doaj-d104f6ffca074252b14d1314f8e7e6ef2021-04-29T23:03:37ZengMDPI AGElectronics2079-92922021-04-01101053105310.3390/electronics10091053A Saliency-Based Patch Sampling Approach for Deep Artistic Media RecognitionHeekyung Yang0Kyungha Min1Division of SW Convergence, Sangmyung University, Seoul 03016, KoreaDepartment of Computer Science, Sangmyung University, Seoul 03016, KoreaWe present a saliency-based patch sampling strategy for recognizing artistic media from artwork images using a deep media recognition model, which is composed of several deep convolutional neural network-based recognition modules. The decisions from the individual modules are merged into the final decision of the model. To sample a suitable patch for the input of the module, we devise a strategy that samples patches with high probabilities of containing distinctive media stroke patterns for artistic media without distortion, as media stroke patterns are key for media recognition. We design this strategy by collecting human-selected ground truth patches and analyzing the distribution of the saliency values of the patches. From this analysis, we build a strategy that samples patches that have a high probability of containing media stroke patterns. We prove that our strategy shows best performance among the existing patch sampling strategies and that our strategy shows a consistent recognition and confusion pattern with the existing strategies.https://www.mdpi.com/2079-9292/10/9/1053media recognitionCNNsaliencypatch sampling |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Heekyung Yang Kyungha Min |
spellingShingle |
Heekyung Yang Kyungha Min A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition Electronics media recognition CNN saliency patch sampling |
author_facet |
Heekyung Yang Kyungha Min |
author_sort |
Heekyung Yang |
title |
A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition |
title_short |
A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition |
title_full |
A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition |
title_fullStr |
A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition |
title_full_unstemmed |
A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition |
title_sort |
saliency-based patch sampling approach for deep artistic media recognition |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2021-04-01 |
description |
We present a saliency-based patch sampling strategy for recognizing artistic media from artwork images using a deep media recognition model, which is composed of several deep convolutional neural network-based recognition modules. The decisions from the individual modules are merged into the final decision of the model. To sample a suitable patch for the input of the module, we devise a strategy that samples patches with high probabilities of containing distinctive media stroke patterns for artistic media without distortion, as media stroke patterns are key for media recognition. We design this strategy by collecting human-selected ground truth patches and analyzing the distribution of the saliency values of the patches. From this analysis, we build a strategy that samples patches that have a high probability of containing media stroke patterns. We prove that our strategy shows best performance among the existing patch sampling strategies and that our strategy shows a consistent recognition and confusion pattern with the existing strategies. |
topic |
media recognition CNN saliency patch sampling |
url |
https://www.mdpi.com/2079-9292/10/9/1053 |
work_keys_str_mv |
AT heekyungyang asaliencybasedpatchsamplingapproachfordeepartisticmediarecognition AT kyunghamin asaliencybasedpatchsamplingapproachfordeepartisticmediarecognition AT heekyungyang saliencybasedpatchsamplingapproachfordeepartisticmediarecognition AT kyunghamin saliencybasedpatchsamplingapproachfordeepartisticmediarecognition |
_version_ |
1721500247434199040 |