دورية أكاديمية
Lychee cultivar fine-grained image classification method based on improved ResNet-34 residual network
العنوان: | Lychee cultivar fine-grained image classification method based on improved ResNet-34 residual network |
---|---|
المؤلفون: | Yiming Xiao, Jianhua Wang, Hongyi Xiong, Fangjun Xiao, Renhuan Huang, Licong Hong, Bofei Wu, Jinfeng Zhou, Yongbin Long, Yubin Lan |
المصدر: | Journal of Agricultural Engineering (2024) |
بيانات النشر: | PAGEPress Publications, 2024. |
سنة النشر: | 2024 |
المجموعة: | LCC:Agriculture LCC:Agriculture (General) |
مصطلحات موضوعية: | Attention mechanism, lychee classification, residual network, transfer learning, Agriculture, Agriculture (General), S1-972 |
الوصف: | Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly. This paper proposes a lychee classification method using an improved ResNet-34 residual network for six common varieties. We enhance the CBAM attention mechanism by replacing the large receptive field in the SAM module with a smaller one. Attention mechanisms are added at key network stages, focusing on crucial image information. Transfer learning is employed to apply ImageNet-trained model weights to this task. Test set evaluations demonstrate that our improved ResNet-34 network surpasses the original, achieving a recognition accuracy of 95.8442%, a 5.58 percentage point improvement. |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 1974-7071 2239-6268 |
Relation: | https://www.agroengineering.org/jae/article/view/1593; https://doaj.org/toc/1974-7071; https://doaj.org/toc/2239-6268 |
DOI: | 10.4081/jae.2024.1593 |
URL الوصول: | https://doaj.org/article/204473287e18493d90b96934a3ad2d8c |
رقم الأكسشن: | edsdoj.204473287e18493d90b96934a3ad2d8c |
قاعدة البيانات: | Directory of Open Access Journals |
تدمد: | 19747071 22396268 |
---|---|
DOI: | 10.4081/jae.2024.1593 |