Rubber Leaf Image Classification Using Artificial Intelligence Methods as an Effort to Improve Plantation Production Results

Abstract

Purpose: Rubber is one of the plantation commodities that contributes positively to the trade surplus in the agricultural sector. Seeing the positive trend in global rubber consumption and production, demand is expected to continue increasing in the future. To enhance rubber productivity, rubber processing technology can be used to make it more efficient, thus increasing the amount of latex extracted from the sap and reducing waste material

Design/methodology/approach: One technology that can be developed to increase the productivity efficiency of rubber plants is by using Artificial Intelligence. This technology is expected to be implemented in the rubber plantation sector, specifically in the automatic recognition of rubber leaves.

Findings/result: The measurement and performance analysis of the rubber leaf image classification algorithm based on Artificial Intelligence has also been evaluated, showing near-perfect accuracy on training data (99.86%) and very good performance on validation data (97.43%), with a very low validation loss (0.0873), indicating that the model has learned well by the last epoch

Originality/value/state of the art: The population in this study consists of image data from various tree leaves, including 10 types of rubber leaves and non-rubber leaves