CONVOLUTIONAL NEURAL NETWORK FOR DETECTION OF NATIVE ORCHID TYPES IN HONDURAS (#1407)
Read ArticleDate of Conference
July 17-19, 2024
Published In
"Sustainable Engineering for a Diverse, Equitable, and Inclusive Future at the Service of Education, Research, and Industry for a Society 5.0."
Location of Conference
Costa Rica
Authors
Palma, Marvin
Carrasco, Alberto
Abstract
The detection and classification of objects in flower farm environments have been a necessary support that should be considered, not only because it facilitated the categorization of flowers but also because it reduced the required time, as it no longer needed to be carried out by an expert. The use of convolutional neural networks has been on the rise in all sectors, whether in the automotive industry, livestock, aviation, among others. This is due to their characteristics that leverage artificial intelligence training to achieve precise and efficient detection and classification of objects, but all these methods had a high cost and could not be manipulated by just anyone. The implementation of this resource, working hand in hand with the YOLOv8 algorithm, represented a significant advancement in the field of flower type detection and classification. Keywords: classification, flower farms, convolutional neural network, YOLO, Python, RoboFlow, artificial intelligence.