Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval
Trademark recognition and retrieval is a vital appliance component of content-based image retrieval (CBIR). Reduction in the semantic gap, attaining more accuracy, reduction in computation complexity, and hence in execution time, are the major challenges in designing and developing a trademark retri...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2018-09-01
|
| Series: | Journal of Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jisys-2018-0083 |
| _version_ | 1818734766949662720 |
|---|---|
| author | Pinjarkar Latika Sharma Manisha Selot Smita |
| author_facet | Pinjarkar Latika Sharma Manisha Selot Smita |
| author_sort | Pinjarkar Latika |
| collection | DOAJ |
| description | Trademark recognition and retrieval is a vital appliance component of content-based image retrieval (CBIR). Reduction in the semantic gap, attaining more accuracy, reduction in computation complexity, and hence in execution time, are the major challenges in designing and developing a trademark retrieval system. The direction of the proposed work takes into account these challenges by implementing trademark image retrieval through deep convolutional neural networks (DCNNs) integrated with a relevant feedback mechanism. The dataset features are optimized through particle swarm optimization (PSO), reducing the search space. These best/optimized features are given to the self-organizing map (SOM) for clustering at the preprocessing stage. The CNN model is trained on feature representations of relevant and irrelevant images, using the feedback information from the user bringing the marked relevant images closer to the query. Experimentation proved a significant performance when evaluated using FlickrLogos-27, FlickrLogos-32, and FlickrLogos-32 PLUS datasets, as illustrated in the performance results section. |
| first_indexed | 2024-12-18T00:10:35Z |
| format | Article |
| id | doaj.art-5399a72d01e24cbba55b97bb4540e55f |
| institution | Directory Open Access Journal |
| issn | 0334-1860 2191-026X |
| language | English |
| last_indexed | 2024-12-18T00:10:35Z |
| publishDate | 2018-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Intelligent Systems |
| spelling | doaj.art-5399a72d01e24cbba55b97bb4540e55f2022-12-21T21:27:41ZengDe GruyterJournal of Intelligent Systems0334-18602191-026X2018-09-0129189490910.1515/jisys-2018-0083Deep CNN Combined With Relevance Feedback for Trademark Image RetrievalPinjarkar Latika0Sharma Manisha1Selot Smita2Shri Shankaracharya Technical Campus, Bhilai (C.G.) 490020, IndiaBhilai Institute of Technology, Bhilai (C.G.) 490020, IndiaShri Shankaracharya Technical Campus, Bhilai (C.G.) 490020, IndiaTrademark recognition and retrieval is a vital appliance component of content-based image retrieval (CBIR). Reduction in the semantic gap, attaining more accuracy, reduction in computation complexity, and hence in execution time, are the major challenges in designing and developing a trademark retrieval system. The direction of the proposed work takes into account these challenges by implementing trademark image retrieval through deep convolutional neural networks (DCNNs) integrated with a relevant feedback mechanism. The dataset features are optimized through particle swarm optimization (PSO), reducing the search space. These best/optimized features are given to the self-organizing map (SOM) for clustering at the preprocessing stage. The CNN model is trained on feature representations of relevant and irrelevant images, using the feedback information from the user bringing the marked relevant images closer to the query. Experimentation proved a significant performance when evaluated using FlickrLogos-27, FlickrLogos-32, and FlickrLogos-32 PLUS datasets, as illustrated in the performance results section.https://doi.org/10.1515/jisys-2018-0083content-based image retrieval (cbir)deep convolutional neural networks (dcnns)particle swarm optimization (pso)self-organizing map (som)relevance feedbacktrademark |
| spellingShingle | Pinjarkar Latika Sharma Manisha Selot Smita Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval Journal of Intelligent Systems content-based image retrieval (cbir) deep convolutional neural networks (dcnns) particle swarm optimization (pso) self-organizing map (som) relevance feedback trademark |
| title | Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval |
| title_full | Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval |
| title_fullStr | Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval |
| title_full_unstemmed | Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval |
| title_short | Deep CNN Combined With Relevance Feedback for Trademark Image Retrieval |
| title_sort | deep cnn combined with relevance feedback for trademark image retrieval |
| topic | content-based image retrieval (cbir) deep convolutional neural networks (dcnns) particle swarm optimization (pso) self-organizing map (som) relevance feedback trademark |
| url | https://doi.org/10.1515/jisys-2018-0083 |
| work_keys_str_mv | AT pinjarkarlatika deepcnncombinedwithrelevancefeedbackfortrademarkimageretrieval AT sharmamanisha deepcnncombinedwithrelevancefeedbackfortrademarkimageretrieval AT selotsmita deepcnncombinedwithrelevancefeedbackfortrademarkimageretrieval |