Rare and Endangered Plant Leaf Identification Method Based on Transfer Learning and Knowledge Distillation

Lin Wu,Zhihao Gu,Jiaqian Guo,Jingjing Yang,Xiao Zhang

doi:10.4018/ijaeis.288037

Abstract

Considering the limited sample size of rare and endangered plant leaves and the issue that leaf identification is mainly conducted using mobile smart devices and other technology with low computing power, this paper proposes a rare and endangered plant leaf identification method based on transfer learning and knowledge distillation. Following the expansion of data sets containing rare and endangered plant leaves, the last fully connected layer was replaced with trained Alexnet, VGG16, GoogLeNet, and ResNet models to conduct transfer learning, and realized a relatively high success rate in identifying images of these species. Then, knowledge distillation was utilized to transfer Alexnet, VGG16, GoogLeNet, and ResNet models into a lightweight model. The experiment results indicate that, compared with other methods, the lightweight rare and endangered plant identification model trained with the methods described in this paper was not only more accurate but also less complex than its alternatives.

Highlights

Plants are an important part of ecological systems and biodiversity
Considering the limited sample size of rare and endangered plant leaves and the issue that leaf identification is mainly conducted using mobile smart devices and other technology with low computing power, this paper proposes a rare and endangered plant leaf identification method based on transfer learning and knowledge distillation
Following the expansion of data sets containing rare and endangered plant leaves, the last fully connected layer was replaced with trained Alexnet, VGG16, GoogLeNet, and ResNet models to conduct transfer learning, and realize a relatively high success rate in identifying images of these species

Summary

INTRODUCTION

Plants are an important part of ecological systems and biodiversity. Protecting plant diversity can benefit the sustainable development of human society (Narzullaev, 2021). No research specially focuses on rare and endangered plant leaf identification In response to these issues, this paper proposes an endangered plant leaf identification method based on transfer learning and knowledge distillation, which guarantees high accuracy and requires fewer convolutional neural network (CNN) parameters. This paper trained a CNN with an endangered plant leaf identification data set to enable the learning of deep features of leaf images. This solved the issues of the low accuracy of artificial leaf identification using superficial characteristics and the absence of having a specialized endangered plant leaf identification model.

LITERATURE REVIEW

METHODOLOGY

Findings

CONCLUSION