IDENTIFIKASI MUTU BUAH NAGA MERAH (Hylocereus Costaricensis) MENGGUNAKAN METODE K-NEAREST NEIGHBOR
Total View This Week0
Total View This Week0
Institusion
Politeknik Negeri Jember
Author
Qomaril, Novia Nurul
Subject
458 - Teknik Informatika
Datestamp
2021-12-17 03:15:04
Abstract :
The process of classifying the quality of dragon fruit (Hylocereus sp) in a conventional way using the visual of the human eye has weaknesses including requiring more energy to sort, different levels of human perception, the level of human consistency in assessing fruit quality is not guaranteed because humans can experience fatigue or human error. This study aims to design and develop a digital image processing program and the K-Nearest Neighbor algorithm for the classification of dragon fruit (Hylocereus Costaricensis) into two quality classes, namely class A and class B. Image processing uses color and texture characteristics. Color feature extraction uses Red, Green, Blue values that have gone through the image segmentation process. Texture feature extraction includes Contrast, Correlation, Energy, Homogeneity values obtained based on GLCM (Gray Level Co - Occurrence Matrix). In this study, several trials of K values were used, namely 1, 3, 5, 7, 9.
The process of classifying the quality of dragon fruit (Hylocereus sp) in a conventional way using the visual of the human eye has weaknesses including requiring more energy to sort, different levels of human perception, the level of human consistency in assessing fruit quality is not guaranteed because humans can experience fatigue or human error. This study aims to design and develop a digital image processing program and the K-Nearest Neighbor algorithm for the classification of dragon fruit (Hylocereus Costaricensis) into two quality classes, namely class A and class B. Image processing uses color and texture characteristics. Color feature extraction uses Red, Green, Blue values that have gone through the image segmentation process. Texture feature extraction includes Contrast, Correlation, Energy, Homogeneity values obtained based on GLCM (Gray Level Co - Occurrence Matrix). In this study, several trials of K values were used, namely 1, 3, 5, 7, 9.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
