Open AccessShallot Quality Classification using HSV Color Models and Size Identification based on Naive Bayes Classifier
Author(s) -
Ajib Susanto,
Z H Dewantoro,
Christy Atika Sari,
De Rosal Ignatius Moses Setiadi,
Eko Hari Rachmawanto,
Ibnu Utomo Wahyu Mulyono
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1577/1/012020
Subject(s) - naive bayes classifier , bayes classifier , classifier (uml) , artificial intelligence , pattern recognition (psychology) , hue , quadratic classifier , computer science , bayes error rate , bayes' theorem , machine learning , mathematics , support vector machine , bayesian probability
This research proposes a method of classification of shallots based on quality using the Naïve Bayes Classifier. The Naïve Bayes classifier is a classifier based on statistics and simple probabilities that are widely used in many sophisticated learning methods today. Shallots are classified into three classes, namely good, medium, and poor quality. To get good classification results, appropriate extraction of features is needed, in this case, color feature extraction is selected with the hue saturation value (HSV) model and to identify the size the area, metric and perimeter calculations are used. To get the right size, some morphological operations such as filling holes and opening are performed. Based on the experimental results on 60 training data and 60 testing data classification shallot quality using Naïve Bayes Classifier produces an accuracy of up to 91.67%.