Agroindustrial Plant for the Classification of Hass Avocados in Real-Time with ResNet-18 Architecture

摘要

The avocado is the fruit with a growing trend in production due to its demand in the world market. Peru currently ranks third in the export of Hass type avocados. For the efficient classification of avocados in good or bad condition, a ResNet-18 algorithm applied to a robust agro-industrial plant was implemented. By using a non-invasive classification we reduce handling damage. The plant consists of a feeder system that continues with a conveyor belt, followed by the image acquisition system with its lighting system, finally, there is the classification system formed by the pneumatic system consisting of pistons that will deposit the avocados in the right containers. The treatment of the images was developed in three stages: acquisition, training, and implementation of the neural network. The Deep Learning algorithm used is ResNet-18, and the hyperparameters of the convolutional network were adjusted to obtain a precision of 98.72%, a specificity of 98.52%, and an F1 score of 98.08%.