Identification of Navel Orange Lesions by Nonlinear Deep Learning Algorithm

Abstract

It is difficult for humans to recognize recessive diseases in navel oranges. Therefore, deep neural networks are applied to plant disease identification. To improve the feature extraction ability of convolutional neural networks, the Parameter Exponential Nonlinear Activation Unit (PENLU) is proposed to replace the activated function of the neural network. This function not only adds multiple parameters but also brings better generalization ability to the neural network. In addition, the proposed function parameters can be updated by the inverse Stochastic Gradient Descent (SGD) algorithm, which has unparalleled advantages over the existing activated functions. The Residual Network (ResNet), improved by PENLU, is applied to navel orange lesion recognition and achieves the most advanced accuracy compared with traditional lesion recognition methods. It is worth mentioning that the data set of navel orange leaf images proposed in this paper will provide samples for subsequent research. The code and model are available at the website https://github.com/xncaffe/caffe_penlu.

Automatic detection and classification of disease in citrus fruit and leaves using a customized CNN based model

“…Some of the potential strategies for diagnosing plant disease are mentioned here. Yang et al (2018), used the Parametric Exponential Nonlinear Unit (PENLU) by relocating the activated functionality of the neural net and enhancing the generalization capability of the neural network to increase the performance of a neural network framework. ResNet processing was improved, and the model was developed using pictures of regional urban navel orange lesions as a basis.…”

Systematic Review of the Early Detection and Classification of Plant Diseases Using Deep Learning

“…In addition, the properties of the dataset are limited to the identification and detection of diseases caused by biological and abiotic factors. However, there are similarities in properties caused by abiotic and biological factors that lead to misdiagnosis such as undernourishment, soil compaction, and water stress [38].…”