Deep Hierarchical Representation from Classifying Logo-405
We introduce a logo classification mechanism which combines a series of deep representations obtained by fine-tuning convolutional neural network (CNN) architectures and traditional pattern recognition algorithms. In order to evaluate the proposed mechanism, we build a middle-scale logo dataset (nam...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-Wiley
2017-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2017/3169149 |
| _version_ | 1798044740510285824 |
|---|---|
| author | Sujuan Hou Jianwei Lin Shangbo Zhou Maoling Qin Weikuan Jia Yuanjie Zheng |
| author_facet | Sujuan Hou Jianwei Lin Shangbo Zhou Maoling Qin Weikuan Jia Yuanjie Zheng |
| author_sort | Sujuan Hou |
| collection | DOAJ |
| description | We introduce a logo classification mechanism which combines a series of deep representations obtained by fine-tuning convolutional neural network (CNN) architectures and traditional pattern recognition algorithms. In order to evaluate the proposed mechanism, we build a middle-scale logo dataset (named Logo-405) and treat it as a benchmark for logo related research. Our experiments are carried out on both the Logo-405 dataset and the publicly available FlickrLogos-32 dataset. The experimental results demonstrate that the proposed mechanism outperforms two popular ways used for logo classification, including the strategies that integrate hand-crafted features and traditional pattern recognition algorithms and the models which employ deep CNNs. |
| first_indexed | 2024-04-11T23:09:05Z |
| format | Article |
| id | doaj.art-bd50167cd8c947a2a6415be9abe21b85 |
| institution | Directory Open Access Journal |
| issn | 1076-2787 1099-0526 |
| language | English |
| last_indexed | 2024-04-11T23:09:05Z |
| publishDate | 2017-01-01 |
| publisher | Hindawi-Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj.art-bd50167cd8c947a2a6415be9abe21b852022-12-22T03:57:54ZengHindawi-WileyComplexity1076-27871099-05262017-01-01201710.1155/2017/31691493169149Deep Hierarchical Representation from Classifying Logo-405Sujuan Hou0Jianwei Lin1Shangbo Zhou2Maoling Qin3Weikuan Jia4Yuanjie Zheng5School of Information Science and Engineering, Shandong Normal University, Jinan 250014, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250014, ChinaSchool of Computer Science, Chongqing University, Chongqing 400030, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250014, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250014, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250014, ChinaWe introduce a logo classification mechanism which combines a series of deep representations obtained by fine-tuning convolutional neural network (CNN) architectures and traditional pattern recognition algorithms. In order to evaluate the proposed mechanism, we build a middle-scale logo dataset (named Logo-405) and treat it as a benchmark for logo related research. Our experiments are carried out on both the Logo-405 dataset and the publicly available FlickrLogos-32 dataset. The experimental results demonstrate that the proposed mechanism outperforms two popular ways used for logo classification, including the strategies that integrate hand-crafted features and traditional pattern recognition algorithms and the models which employ deep CNNs.http://dx.doi.org/10.1155/2017/3169149 |
| spellingShingle | Sujuan Hou Jianwei Lin Shangbo Zhou Maoling Qin Weikuan Jia Yuanjie Zheng Deep Hierarchical Representation from Classifying Logo-405 Complexity |
| title | Deep Hierarchical Representation from Classifying Logo-405 |
| title_full | Deep Hierarchical Representation from Classifying Logo-405 |
| title_fullStr | Deep Hierarchical Representation from Classifying Logo-405 |
| title_full_unstemmed | Deep Hierarchical Representation from Classifying Logo-405 |
| title_short | Deep Hierarchical Representation from Classifying Logo-405 |
| title_sort | deep hierarchical representation from classifying logo 405 |
| url | http://dx.doi.org/10.1155/2017/3169149 |
| work_keys_str_mv | AT sujuanhou deephierarchicalrepresentationfromclassifyinglogo405 AT jianweilin deephierarchicalrepresentationfromclassifyinglogo405 AT shangbozhou deephierarchicalrepresentationfromclassifyinglogo405 AT maolingqin deephierarchicalrepresentationfromclassifyinglogo405 AT weikuanjia deephierarchicalrepresentationfromclassifyinglogo405 AT yuanjiezheng deephierarchicalrepresentationfromclassifyinglogo405 |