Classification of coffee beans using Deep Learning

Resumo

The global agribusiness of coffee includes, annually, resources that reach 91 billion dollars and involves
half a billion people. The coffee market is characterized by a set of activities of enormous complexity, dynamism,
and a growing level of demand from consumers regarding the quality of the drink. This imposes high quality
control on producing, consuming, and exporting countries. Currently, the definition of the quality and therefore
the value of coffee is based on manual classification, that is, a person plays the role of a trained (certified) classifier
to qualify coffee samples. Thus, the current classification process suffers from the subjectivity of the classifiers
and a great difficulty in standardizing the process due to possible inconsistencies in the process. Given this
scenario, the present work proposes to develop a system for classifying coffee samples considering shape and
imperfections. The classification process will be done by using computer vision through Deep Learning and
regional convolutional networks (R-CNN) where the intrinsic defects present in the sample will be identified.
Among the benefits of automating the coffee classification process, the following stand out: Cost reduction, agility
and standardization of the classification.