Development of a cacao bean classification system using image processing and artificial neural network /
by Gwyneth Mae I. Bautista and Nobie-Ann L. Quiñones.
- Indang, Cavite : Cavite State University- Main Campus, 2022.
- xiii, 86 pages : illustrations ; 28 cm
Design Project (Bachelor of Science in Electronics and Communications Engineering) Cavite State University.
Includes bibliographical references.
College of Engineering and Information Technology (CEIT) College of Engineering and Information Technology (CEIT)
BAUTISTA, GWYNETH MAE., and QUIÑONES, NOBIE-ANN. Development of a Cacao Bean Classification System Using Image Processing and Artificial Neural Network. Undergraduate Project Design. Bachelor of Science in Electronics Engineering. Cavite State University, Indang, Cavite. December 2018. Adviser: Edwin R.Arboleda, DEng. Using an image processing method and an artificial neural network model, this paper outlines the development of a prototype for identifying the quality of cacao beans based on the color of its interior. The Philippine National Standards for cacao beans were used as the basis for the system's set of guidelines and standards. The prototype was able to automatically determine the classifications of hybrid Trinitario cacao beans cultivated at Dariano Cacao Farm in Silang, which is located in the province of Cavite in the Philippines. The images employed as the data samples of the project were captured using a camera in a controlled setting. The sample images that have been loaded to the system consisted of 13 cacao beans that were placed in the prototype's sample drawer. Thereafter, the photographs are transferred to the system of the prototype, which then crops each of the 13 cacao beans individually and segments the characteristics of each image based on the RGB values. Classification experiments on 260 cross-cut hybrid Trinitario cacao beans using the artificial neural network classifier yielded an overall accuracy of 91.65 percent. The findings indicate that the developed image processing technique and the Artificial Neural Network or ANN-based classifier have the potential to be used as an efficient instrument for the purpose of classifying cacao beans.