<![CDATA[Characteristic recognition of biological sciences is increasingly popular in scientific research, especially by utilizing computation.Indonesia is one of the countries with the largest biodiversity in the world, currently, Indonesia has identified and named 19,232 species of flowering plants.Flower image classification has attracted the interest of many researchers to investigate new methods.One of the widely used methods is deep learning and neural network methods.Convolutional Neural Network (CNN) is one of the most commonly used deep learning methods in image processing. This study aims to analyze the performance of flower image classification using VGG16 and NasNetMobile architecture with fine tune and without fine tune.The NasNetMobile architecture model with fine tune achieved the best accuracy of 99.15%, while the NasNetMobile architecture model without fine tune achieved the lowest accuracy of 97.45%.]]>
Copyrights © 2024
