Estimation of fruit number in coffee trees by maturity level, based on color space weighting, using a new segmentation algorithm

Abstract

Computer vision systems are essential for automating agricultural tasks such as disease detection and fruit defect identification. However, their application in coffee farming faces significant  challenges due to environmental variability and the complex structure of coffee trees, which complicate image acquisition. Thus, this study addresses two key questions: 1) Can low-cost, user-friendly  equipment adapt to crop conditions while ensuring image quality? 2) Can a computer vision algorithm accurately count and classify coffee beans with over 80% accuracy using data from low-cost cameras?  To answer these questions, an image acquisition system was developed based on the phenological characteristics of coffee plants, ensuring focused and consistent image capture. Additionally, a novel  algorithm was created, utilizing statistical analysis of color spaces to effectively separate fruits from the  background, segment images, and count fruits. The algorithm achieved accuracy rates, when  compared with a traditional approach, within the desired range for each coffee fruit class: green (83%),  green-olive (79%), cherry (86%), and raisin (80%). These results demonstrate the potential of this approach for accurate and efficient fruit processing in coffee farming, particularly when images are  captured directly from tree branches.