SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN

作者：

Highlights：

• An accurate plant recognition system with maximum resemblance to botanist behavior.

• A low-cost, on-site, fast, easy-to-use, and substitute system for botanical labs.

• Based on transfer-learning and three distributable convolutional neural networks.

• Employing two from-scratch-designed models, MobileNetV2 model, and Visualizing layers.

• Outperforming the state-of-the-art methods on Flavia and MalayaKew datasets.

摘要

•An accurate plant recognition system with maximum resemblance to botanist behavior.•A low-cost, on-site, fast, easy-to-use, and substitute system for botanical labs.•Based on transfer-learning and three distributable convolutional neural networks.•Employing two from-scratch-designed models, MobileNetV2 model, and Visualizing layers.•Outperforming the state-of-the-art methods on Flavia and MalayaKew datasets.

论文关键词：SWP-LeafNET,Deep learning,Plant leaf recognition,Convolutional neural network

论文评审过程：Received 17 April 2020, Revised 22 April 2022, Accepted 28 April 2022, Available online 2 May 2022, Version of Record 6 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117470