{"title":"兰花识别中预训练深度学习模型的集成投票方法","authors":"Chia-Ho Ou, Yi-Nuo Hu, Dong-Jie Jiang, Po-Yen Liao","doi":"10.1109/SysCon53073.2023.10131263","DOIUrl":null,"url":null,"abstract":"Orchids are a diverse group of angiosperms, many of which share similar physical characteristics such as color, pattern, and inflorescence. As a result, identifying orchid species can be a time-consuming task that requires expert knowledge. This paper proposes a solution that utilizes Convolutional Neural Networks (CNNs) for accurate and efficient image classification. Specifically, three pre-trained models, ResNet50, EfficientNet, and Big Transfer (BiT), were employed and fine-tuned using transfer learning. Ensemble learning was then employed to combine the predicted probabilities of the three models, weighted by their respective performance, to determine the orchid species through soft voting. The proposed approach was validated using the Orchid Flowers Dataset, selecting 84 varieties, and achieved a maximum accuracy of 84.67%, improving upon the best single model by 2.8%. The Orchid-52 dataset also demonstrated a 3.1% improvement, reaching 95.13% accuracy.","PeriodicalId":169296,"journal":{"name":"2023 IEEE International Systems Conference (SysCon)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Ensemble Voting Method of Pre-Trained Deep Learning Models for Orchid Recognition\",\"authors\":\"Chia-Ho Ou, Yi-Nuo Hu, Dong-Jie Jiang, Po-Yen Liao\",\"doi\":\"10.1109/SysCon53073.2023.10131263\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Orchids are a diverse group of angiosperms, many of which share similar physical characteristics such as color, pattern, and inflorescence. As a result, identifying orchid species can be a time-consuming task that requires expert knowledge. This paper proposes a solution that utilizes Convolutional Neural Networks (CNNs) for accurate and efficient image classification. Specifically, three pre-trained models, ResNet50, EfficientNet, and Big Transfer (BiT), were employed and fine-tuned using transfer learning. Ensemble learning was then employed to combine the predicted probabilities of the three models, weighted by their respective performance, to determine the orchid species through soft voting. The proposed approach was validated using the Orchid Flowers Dataset, selecting 84 varieties, and achieved a maximum accuracy of 84.67%, improving upon the best single model by 2.8%. The Orchid-52 dataset also demonstrated a 3.1% improvement, reaching 95.13% accuracy.\",\"PeriodicalId\":169296,\"journal\":{\"name\":\"2023 IEEE International Systems Conference (SysCon)\",\"volume\":\"140 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE International Systems Conference (SysCon)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SysCon53073.2023.10131263\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE International Systems Conference (SysCon)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SysCon53073.2023.10131263","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
兰花是被子植物的一个多样化的群体,其中许多具有相似的物理特征,如颜色,图案和花序。因此,鉴定兰花种类可能是一项耗时的任务,需要专业知识。本文提出了一种利用卷积神经网络(cnn)进行准确高效图像分类的解决方案。具体来说,三个预训练模型,ResNet50, EfficientNet和Big Transfer (BiT),被使用并使用迁移学习进行微调。然后使用集成学习将三个模型的预测概率结合起来,根据各自的表现加权,通过软投票确定兰花种类。利用兰花花数据集(Orchid Flowers Dataset)对该方法进行了验证,选择了84个品种,获得了84.67%的最大准确率,比最佳单一模型提高了2.8%。兰花-52数据集的准确率也提高了3.1%,达到95.13%。
An Ensemble Voting Method of Pre-Trained Deep Learning Models for Orchid Recognition
Orchids are a diverse group of angiosperms, many of which share similar physical characteristics such as color, pattern, and inflorescence. As a result, identifying orchid species can be a time-consuming task that requires expert knowledge. This paper proposes a solution that utilizes Convolutional Neural Networks (CNNs) for accurate and efficient image classification. Specifically, three pre-trained models, ResNet50, EfficientNet, and Big Transfer (BiT), were employed and fine-tuned using transfer learning. Ensemble learning was then employed to combine the predicted probabilities of the three models, weighted by their respective performance, to determine the orchid species through soft voting. The proposed approach was validated using the Orchid Flowers Dataset, selecting 84 varieties, and achieved a maximum accuracy of 84.67%, improving upon the best single model by 2.8%. The Orchid-52 dataset also demonstrated a 3.1% improvement, reaching 95.13% accuracy.