Jasmine Flower Classification with CNN Architectures: A Comparative Study of NasNetMobile, VGG16, and Xception in Agricultural Technology

Abstract

Jasmine flowers have many benefits and uses such as for traditional medicine, tea, perfume, cosmetics, decoration, and others. in the selection of fresh jasmine flowers for making tea is very important, currently the classification of jasmine flowers for making tea is mostly still using manual methods. Often influenced by individual preferences, opinions, or biases. this causes a lack of objectivity and uncertainty in the classification of jasmine flowers. The manual method is very weak due to human visual limitations and fatigue levels which can result in less than the optimal jasmine flower classification. Therefore, in the research that has been done, a transfer learning system was applied that can classify fresh jasmine flowers with rotten jasmine flowers. This study aims to compare three different Convolutional Neural Network architectures: NasNetMobile, VGG16, and Xception. The results on the three architectures can show maximum results, namely 99.21% for NasNetMobile, 98.69% for VGG16 and 97.91% for Xception. This study provides insight into the classification of good and bad jasmine flowers to encourage further exploration in the field of agriculture.