Open AccessSeed of rice plant classification using coarse tree classifier
Author(s) -
Kim Wallie Vergara Geollegue,
Edwin R. Arboleda,
Andy Agustin Dizon
Publication year - 2022
Publication title -
iaes international journal of artificial intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.341
H-Index - 7
eISSN - 2252-8938
pISSN - 2089-4872
DOI - 10.11591/ijai.v11.i2.pp727-735
Subject(s) - rgb color model , computer science , classifier (uml) , artificial intelligence , feature extraction , pattern recognition (psychology) , computer vision
The goal of this paper is to help the agriculture to have consistent observation in the status of seeds in rice plants and have a good quality postproduction by classifying the seeds automatically leading to reduction of low-quality rice plants while achieving higher demands in exportation as the quality increases. Additionally, manually observing the seeds of rice plants does not give an accurate evaluation as factors such as fatigue and emotion can affect the result. Using image processing and color feature extraction, it extracted the red, green, and blue (RGB) color feature lying in the pixel point of the seed in the healthy and unhealthy images of rice plants and classified by coarse tree classifier (CTC). The classifier achieved a 100% accuracy and training time of 0.32189 seconds, hence the fitted machine learning approach in the study.