Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link
To ameliorate the precision of clothing image classification, we proposed a clothing image classification method via the DenseNet201 network based on transfer learning and the optimized regularized random vector functional link (RVFL). First, the formula extracts weight’s parameters about DenseNet20...
| Glavni autori: | , , , , |
|---|---|
| Format: | Članak |
| Jezik: | English |
| Izdano: |
Taylor & Francis Group
2023-04-01
|
| Serija: | Journal of Natural Fibers |
| Teme: | |
| Online pristup: | http://dx.doi.org/10.1080/15440478.2023.2190188 |
| _version_ | 1827807871784452096 |
|---|---|
| author | Zhiyu Zhou Mingxuan Liu Wenxiong Deng Yaming Wang Zefei Zhu |
| author_facet | Zhiyu Zhou Mingxuan Liu Wenxiong Deng Yaming Wang Zefei Zhu |
| author_sort | Zhiyu Zhou |
| collection | DOAJ |
| description | To ameliorate the precision of clothing image classification, we proposed a clothing image classification method via the DenseNet201 network based on transfer learning and the optimized regularized random vector functional link (RVFL). First, the formula extracts weight’s parameters about DenseNet201 that is pre-trained on the ImageNet dataset for transfer learning, thereby obtaining an incipient network，after that trim this model parameters. The modified network is utilized to pick up the clothing image features output by the DenseNet201’s global average pooling layer. Second, regularization coefficient is introduced to control RVFL’s model complexity and solve the problem of over-fitting. Then, the generated solution vector of aquila optimizer (AO) is produced by marine predators algorithm (MPA). The input weights, biases of hidden layer and renormalization modulus of regularized RVFL are optimized using the improved AO algorithm. Finally, we use the optimized RVFL to assort abstracted fashion graphics traits. We use Accuracy, Macro-F1, Macro-R and Macro-P to assess the algorithm’s ability and compare this algorithm with ResNet50 network, ResNet101 network, DenseNet201 network, InceptionV3 network and different classifiers, which use DenseNet201 as the feature extractor to get the input. From the experimental results, this algorithm proposed has excellent classification power and generalization ability. |
| first_indexed | 2024-03-11T22:03:02Z |
| format | Article |
| id | doaj.art-c32da1de7a9a42799a0a52cce684deca |
| institution | Directory Open Access Journal |
| issn | 1544-0478 1544-046X |
| language | English |
| last_indexed | 2024-03-11T22:03:02Z |
| publishDate | 2023-04-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Natural Fibers |
| spelling | doaj.art-c32da1de7a9a42799a0a52cce684deca2023-09-25T10:29:00ZengTaylor & Francis GroupJournal of Natural Fibers1544-04781544-046X2023-04-0120110.1080/15440478.2023.21901882190188Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional LinkZhiyu Zhou0Mingxuan Liu1Wenxiong Deng2Yaming Wang3Zefei Zhu4Zhejiang Sci-Tech UniversityZhejiang Sci-Tech UniversityZhejiang Sci-Tech UniversityLishui UniversityHangzhou Dianzi UniversityTo ameliorate the precision of clothing image classification, we proposed a clothing image classification method via the DenseNet201 network based on transfer learning and the optimized regularized random vector functional link (RVFL). First, the formula extracts weight’s parameters about DenseNet201 that is pre-trained on the ImageNet dataset for transfer learning, thereby obtaining an incipient network，after that trim this model parameters. The modified network is utilized to pick up the clothing image features output by the DenseNet201’s global average pooling layer. Second, regularization coefficient is introduced to control RVFL’s model complexity and solve the problem of over-fitting. Then, the generated solution vector of aquila optimizer (AO) is produced by marine predators algorithm (MPA). The input weights, biases of hidden layer and renormalization modulus of regularized RVFL are optimized using the improved AO algorithm. Finally, we use the optimized RVFL to assort abstracted fashion graphics traits. We use Accuracy, Macro-F1, Macro-R and Macro-P to assess the algorithm’s ability and compare this algorithm with ResNet50 network, ResNet101 network, DenseNet201 network, InceptionV3 network and different classifiers, which use DenseNet201 as the feature extractor to get the input. From the experimental results, this algorithm proposed has excellent classification power and generalization ability.http://dx.doi.org/10.1080/15440478.2023.2190188densenet201marine predators algorithmaquila optimizerregularized random vector functional linkclothing classification |
| spellingShingle | Zhiyu Zhou Mingxuan Liu Wenxiong Deng Yaming Wang Zefei Zhu Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link Journal of Natural Fibers densenet201 marine predators algorithm aquila optimizer regularized random vector functional link clothing classification |
| title | Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link |
| title_full | Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link |
| title_fullStr | Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link |
| title_full_unstemmed | Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link |
| title_short | Clothing Image Classification with DenseNet201 Network and Optimized Regularized Random Vector Functional Link |
| title_sort | clothing image classification with densenet201 network and optimized regularized random vector functional link |
| topic | densenet201 marine predators algorithm aquila optimizer regularized random vector functional link clothing classification |
| url | http://dx.doi.org/10.1080/15440478.2023.2190188 |
| work_keys_str_mv | AT zhiyuzhou clothingimageclassificationwithdensenet201networkandoptimizedregularizedrandomvectorfunctionallink AT mingxuanliu clothingimageclassificationwithdensenet201networkandoptimizedregularizedrandomvectorfunctionallink AT wenxiongdeng clothingimageclassificationwithdensenet201networkandoptimizedregularizedrandomvectorfunctionallink AT yamingwang clothingimageclassificationwithdensenet201networkandoptimizedregularizedrandomvectorfunctionallink AT zefeizhu clothingimageclassificationwithdensenet201networkandoptimizedregularizedrandomvectorfunctionallink |