Deep Learning with Auxiliary Learning Attention Mechanism for Oil Palm Fruit Image Ripeness Classification
Currently the available oil palm fruit ripeness classification models are lacking in accuracy and reliability. As the consequence, the automation of oil palm fruit ripeness sorting is not pervasive in the industry. This is unfortunate, because oil palm is one of the leading commodities in agriculture industry, especially in Indonesia. To improve the accuracy, we propose a deep learning model with an addition-based attention mechanism as an oil palm fruit ripeness classification system. The result of this study shows that the proposed model improved the accuracy of the best previous deep learning model by 9.85%.
ICIC Express Letters
Herman Herman, Albert Susanto, Tjeng Wawan Cenggoro, Dedy Ariansyah, Bens Pardamean