Flowering and fruit ripening quantification by image analysis to forecast coffee production

• Grant number: 22/14831-0
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: December 01, 2022
• End date: November 30, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: MCTI/MC
• Principal Investigator: Antonio Chalfun Junior
• Grantee: Muhammad Noman
• Host Institution: Pró-Reitoria de Pós-Graduação. Universidade Federal de Lavras (UFLA). Ministério da Educação (Brasil). Lavras , SP, Brazil
• Associated research grant: 21/06968-3 - From seed to cup: internet of things technology in the quality coffee production chain, AP.TEM

Abstract

The mechanisms that influence coffee quality are complex and involve factors such as genetics, cultivation conditions, post-harvest processing, toast and drink preparation. Multidisciplinary teams are necessary for the development of research and technologies at critical and strategic points of this coffee production chain so that the farmer is able to make assertive decisions to obtain quality coffees. However, the connection between all these factors and the final quality of the drink has not yet been explored. Thus, combining the use of sensors and internet of things to collect and cross data from the coffee production chain, accurate information can be accessed by producers who will have better reproducibility conditions of the desired quality. Thus, this type of technology, which has minimal human intervention, can be used by producers by assisting them in controlling and improving steps from cultivation to consumer table. The project aims to elaborate an automated methodology for flowering and fruit ripening analyses in coffee by massive image capture, light manipulation and development of a program (algorithm/software) for digitization and data analysis. The desired results are quantitative, seeking to establish numerical patterns of floral proportion and ripening distribution in plants from the output data of an algorithm developed for this goal. Project applications extend to data capture and supporting field corrective management, in other words focused on precision agriculture. At the end of the project we hope to offer a tool capable of quantifying the number of annual flowers, determining the homogeneity of flowering and estimating the production of fruits and its maturation. These data will compose a database that will be updated annually and with prospect of use, along with artificial intelligence and machine learning algorithms, to create an index that anticipates and improve productivity forecasting. Thus, we hope that the new tool will be of great interest in the field of biotechnology and agribusiness. (AU)