Image of PEMBANGUNAN SISTEM SORTIR JERUK SUNKIST LOKAL OTOMATIS DENGAN METODE K-NEAREST NEIGHBOR
Bookmark Share

Skripsi

PEMBANGUNAN SISTEM SORTIR JERUK SUNKIST LOKAL OTOMATIS DENGAN METODE K-NEAREST NEIGHBOR

The increasing demand for local Sunkist oranges, especially during certain periods, has led to a growing need for an accurate and efficient fruit sorting process. Manual sorting methods are prone to classification errors, which may result in distribution losses, reduced fruit quality, and potential health risks to consumers. Therefore, this study aims to develop an automatic quality identification system for local Sunkist oranges based on digital image processing using the K-Nearest Neighbor (K-NN) method. The dataset used in this research consists of 90 images of local Sunkist oranges classified into three categories: unripe, ripe, and rotten. Image acquisition was performed using a webcam installed on a lighting chamber to ensure stable illumination and reduce background interference. The image processing stages include center-area cropping with a size of 20×20 pixels, extraction of Red, Green, and Blue (RGB) color intensity values, and data normalization using the Min-Max Scaling method. The classification process was carried out using the K-NN method with a K value of 3 and Euclidean distance calculation. Experimental results show that the proposed system is able to classify the maturity level of local Sunkist oranges with an overall accuracy of 92.6%. These results indicate that the RGB-based K-NN classification method is effective and feasible to be used as a foundation for developing an automatic sorting system for local Sunkist oranges.

Availability
#
Central Library (Reference) T1903982025
T190398
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1903982025
Publisher
Indralaya : Prodi Teknik Mesin, Fakultas Teknik Universitas Sriwijaya.,
Collation
xxvii, 56 hlm.; ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
629.895 07
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Metode K-Nearest Neighbor
Prodi Teknik Mesin
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment