A Multi-Plant Disease Diagnosis Method using Convolutional Neural Network

TL;DR

This paper proposes a multi-plant disease diagnosis method using convolutional neural networks that can identify multiple plants and their diseases simultaneously, improving over models that only diagnose specific plants.

Contribution

The study introduces a multi-label CNN model capable of diagnosing diseases across six different plants, utilizing architectures like Xception and DenseNet for enhanced accuracy.

Findings

Xception and DenseNet outperform other CNN architectures in multi-plant disease classification.

Skip connections and spatial convolutions improve model performance.

The model can diagnose multiple plants and diseases in parallel.

Abstract

A disease that limits a plant from its maximal capacity is defined as plant disease. From the perspective of agriculture, diagnosing plant disease is crucial, as diseases often limit plants' production capacity. However, manual approaches to recognize plant diseases are often temporal, challenging, and time-consuming. Therefore, computerized recognition of plant diseases is highly desired in the field of agricultural automation. Due to the recent improvement of computer vision, identifying diseases using leaf images of a particular plant has already been introduced. Nevertheless, the most introduced model can only diagnose diseases of a specific plant. Hence, in this chapter, we investigate an optimal plant disease identification model combining the diagnosis of multiple plants. Despite relying on multi-class classification, the model inherits a multilabel classification method to identify the plant and the type of disease in parallel. For the experiment and evaluation, we collected data from various online sources that included leaf images of six plants, including tomato, potato, rice, corn, grape, and apple. In our investigation, we implement numerous popular convolutional neural network (CNN) architectures. The experimental results validate that the Xception and DenseNet architectures perform better in multi-label plant disease classification tasks. Through architectural investigation, we imply that skip connections, spatial convolutions, and shorter hidden layer connectivity cause better results in plant disease classification.