Convolutional neural networks identify disease in pequi tree branches
Use Of Convolutional Neural Networks In Detection Of Branch Dieback Disease In Pequi Trees
Computer Vision and Pattern RecognitionComputational Engineering, Finance, and ScienceDatabases
Summary
Pequi trees can get a disease that harms their branches and fruits. The authors tested several types of computer programs called convolutional neural networks to spot this disease by looking at pictures of leaves and branches. They compared different programs to find which one spots sick trees best. This helps farmers and environmentalists catch problems early to protect the trees and their fruit.
What this means in practice
- •For agriculture technology teams: Detect branch dieback disease in pequi orchards early using machine learning models trained on images of leaves and branches.
- •For forest management teams: Monitor health of pequi trees in natural reserves by automatically identifying disease signs from photographic surveys.
Authors
Ronilson Rodrigues Pinho, Elua Ramos Coutinho, Nilza de Lima Pereira Sales, Sildenir Aalves Ribeiro, Sergio Manuel Serra da Cruz
Abstract
This study aims to evaluate and compare convolutional neural network (CNN) architectures, specifically AlexNet, Inception, LeNet, VGG16, and MobileNet, for diagnosing branch dieback (seca-dos-ponteiros) in pequi trees (Caryocar brasiliense). This disease represents a severe threat to tree development and fruit yield, causing substantial economic and ecological losses. The methodology implements computer vision techniques using Python libraries, including Scikit-learn, NumPy, TensorFlow, and Matplotlib, to process and evaluate visual data. The CNN models analyze images of leaves, branches, and flower spikes to detect pathological patterns, such as alterations in texture and coloration. Ultimately, this comparative analysis identifies the most effective architecture for accurately distinguishing healthy plants from diseased ones.