A comparative study of fine-tuning deep learning models for plant disease identification

By Edna Chebet Too, Li Yujian, Sam Njuki, L. Yingchun. Computers and Electronics in Agriculture, 2019

1,257 citations recorded by the source corpus.

Abstract Deep learning has recently attracted a lot of attention with the aim to develop a quick, automatic and accurate system for image identification and classification. In this work, the focus was on fine-tuning and evaluation of state-of-the-art deep convolutional neural network for image-based plant disease classification. An empirical comparison of the deep learning architecture is done. The architectures evaluated include VGG 16, Inception V4, ResNet with 50, 101 and 152 layers and DenseNets with 121 layers. The data used for the experiment is 38 different classes including diseased and healthy images of leafs of 14 plants from plantVillage. Fast and accurate models for plant disease identification are desired so that accurate measures can be applied early. Thus, alleviating the problem of food security. In our experiment, DenseNets has tendency’s to consistently improve in accuracy with growing number of epochs, with no signs of overfitting and performance deterioration. Moreover, DenseNets requires a considerably less number of parameters and reasonable computing time to achieve state-of-the-art performances. It achieves a testing accuracy score of 99.75% to beat the rest of the architectures. Keras with Theano backend was used to perform the training of the architectures.

Subfields: Analytical Chemistry, Plant Science

View Paper: https://www.semanticscholar.org/paper/ee5ba351792839ccc217d667eb077fe68acfbac3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Plant Science

Citations in the corpus

A Survey of Deep Convolutional Neural Networks Applied for Prediction of Plant Leaf Diseases (2021, methodology): “It gives all values in a range from 0 to 1 across all channels without disturbing the view of images [20].”
Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic Stress (2019, methodology): “Several studies were carried out using the PlantVillage dataset (Mohanty et al., 2016; Too et al., 2019; Kaya et al., 2019), most of these studies presented results greater than 99% of accuracy.”
Plant leaf disease classification using EfficientNet deep learning model (2021, result): “The results of studies (Chen et al., 2020b; Geetharamani and Pan-dian, 2019; Mohanty et al., 2016; Too et al., 2019) dealing with diseases of all plant species in PlantVillage dataset were compared with the re-sults of our study and shown in Table 9.”
An advanced deep learning models-based plant disease detection: A review of recent research (2023, background): “(Too et al., 2019) discovered that as the number of iterations grew, the accuracy of dense nets improved when employing fine and contrast parameters.”
COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images (2020, methodology): “Although the ResNet is similar to the VGGNet, it is approximately eight times deeper [38].”