A computer vision system for automatic cherry beans detection on coffee trees

Coffee production estimation is an essential task for coffee farmers in terms of money investment and planning time. In Colombia, the traditional methodology to estimate the total amount of cherry coffee beans is through direct measurements in the field; leave out the cherry beans collected of coffee production (destructive sampling). The cherry coffee dropped in this process cannot be harvest by the producer. In this sense, we found several shortcomings in this methodology as counting errors in the sampling process, insufficient coffee bean samples, significant expenses of costs and time, and coffee beans losses. To handle these issues, we propose a classic Computer Vision (CV) approach to detect cherry beans in coffee trees. This approach substitutes the destructive counting method as a first step to estimate coffee production. To evaluate the CV proposed, seven coffee farmers counted the number of cherry beans on 600 images of coffee trees (castillo, bourbon, and caturra varieties) by human visual perception (ground truth). From evaluations of coffee farmers, we computed statistical measures like precision, recall and, F1-score. The CV system achieved the best results for bourbon coffee trees with 0.594 of precision; 0.669 of total relevant cherry beans correctly classified. (C) 2020 Elsevier B.V. All rights reserved.