Date of Publication
12-2022
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Electronics and Communications Engineering
Subject Categories
Electrical and Computer Engineering
College
Gokongwei College of Engineering
Department/Unit
Electronics And Communications Engg
Thesis Advisor
Carlo Noel E. Ochotorena
Ann E. Dulay
Defense Panel Chair
Edwin Sybingco
Defense Panel Member
John Anthony C. Jose
Reggie C. Gustilo
Abstract/Summary
One of the most pivotal stages of coffee production is the roasting process, as it determines the quality of the beverage. The final measure of the degree of roast is determined by the color of the bean. Visual inspection of the bean color using the naked eye can be a source of inconsistency since many factors are involved. For instance, the human visual system (HVS) exhibits chromatic adaptation where the perceived color of an object is affected by the color of the ambient light, and assessment of color is a subjective task that may cause inconsistencies. Professional roasters use an Agtron Process Analyzer to objectively measure the degree of roast, but measurement can only be done after the coffee beans are cooled. Thus, no changes can be made if the roast level is under or over the desired degree. Hence, this study proposes to create a device made of an LED module, microcontroller, and a camera that will measure the degree of roast in real-time by quantifying the amount of light reflected at different wavelengths by the coffee beans during the roasting process. The process involves using a Convolutional Neural Network (CNN) that extracts features from the images in the dataset and generates a reflectance output and Regression that will manipulate the data and will yield an Agtron number that is used in the determination of the coffee Roast degree. The Real-time measurement of the Agtron number aims to lessen the human subjectivity in the determination of the coffee roast degree and set a gauge of measurement of the doneness of the coffee beans during the roasting process.
Abstract Format
html
Language
English
Format
Electronic
Keywords
Image processing; Coffee—Processing; Coffee—Imaging
Recommended Citation
Andres, J. L., Araño, A. C., Diwara, D. V., & Sazon, C. M. (2022). Real-time spectrophotometric determination of coffee roast degree. Retrieved from https://animorepository.dlsu.edu.ph/etdb_ece/22
Upload Full Text
wf_yes
Embargo Period
12-9-2022
