Identification of arabica coffee post-harvest processing using a convolutional neural network Masud Effendi (a*), Maulana Muhamad Faqy (a), Imam Santoso (a), Retno Astuti (a), Wayan Firdaus Mahmudy (b)
(a) Department of Agroindustrial Technology, Faculty of Agricultural Technology, Universitas Brawijaya
*mas.ud[at]ub.ac.id
(b) Faculty of Computer Science, Universitas Brawijaya
Abstract
Indonesia^s economy is greatly boosted by coffee, one of its flagship commodities. The post-harvest processing of coffee involves various processes, and the different methods have a crucial connection to the subsequent stages. Digital image analysis using Convolutional Neural Network (CNN) methods can be utilized to improve the identification of coffee beans. This study uses CNN with the ResNet-18 and MobileNetV2 architectures for image analysis. Both architectures achieved the same highest accuracy of 98.89% with a data proportion of 70:20:10. The study demonstrates that both ResNet-18 and MobileNetV2 architectures perform equally well in identifying the post-harvest processing of arabica coffee. The choice between the two can be considered based on available computational resources, desired model weight size, and relevant data proportion requirements for the desired application.
Keywords: Image Processing- MobileNetV2- ResNet-18- arabica coffe- Batu
Topic: Agro-industrial production system management and regulation
