AUTHOR=Figueroa-Flores Carola , San-Martin Pablo 

TITLE=Deep learning for Chilean native flora classification: a comparative analysis

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1211490

DOI=10.3389/fpls.2023.1211490

ISSN=1664-462X

ABSTRACT=The limited availability of information on Chilean native flora has resulted in a lack of knowledge among the general public, and classifying these plants can be a challenging task without extensive expertise. Thankfully, advancements in image classification systems have made daily tasks easier for humans. This study aims to compare various Deep learning (DL) models for the task of classifying images of Chilean native flora. The models evaluated include InceptionV3, VGG19, ResNet152 and MobileNetV2 pre-trained on Imagenet. A dataset consisting of 500 images for each of the 10 classes of native flowers in Chile was created, resulting in a total of 5000 images.