Penerapan Ekstraksi Fitur HSV dan PCA Untuk Klasifikasi Jenis Biji Kopi Menggunakan Algoritma SVM

Faridah, Raisah Nurul (2025) Penerapan Ekstraksi Fitur HSV dan PCA Untuk Klasifikasi Jenis Biji Kopi Menggunakan Algoritma SVM. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (cover) 21081010105.-cover.pdf Download (2MB)
	Text (bab 1) 21081010105.-bab1.pdf Download (211kB)
	Text (bab 2) 21081010105.-bab2.pdf Restricted to Repository staff only until 19 June 2027. Download (626kB)
	Text (bab 3) 21081010105.-bab3.pdf Restricted to Repository staff only until 19 June 2027. Download (808kB)
	Text (bab 4) 21081010105.-bab4.pdf Restricted to Repository staff only until 19 June 2027. Download (1MB)
	Text (bab 5) 21081010105.-bab5.pdf Download (230kB)
	Text (daftar pustaka) 21081010105.-daftarpustaka.pdf Download (211kB)

Abstract

This research aims to develop a classification system for Wonosalam coffee bean types, Arabica, Robusta, and Excelsa using a combination of HSV feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and the Support Vector Machine (SVM) classification algorithm. Manual classification is often subjective, time-consuming, and requires expert knowledge. Errors in distinguishing coffee bean types can affect both taste and market value. Therefore, a digital image processing approach is expected to improve the efficiency and accuracy of the identification process. The dataset consists of 750 roasted coffee bean images that underwent preprocessing and conversion to the HSV (Hue, Saturation, Value) color space. PCA was applied to reduce feature dimensions before classification using SVM. The experimental results show that the SVM model with an RBF kernel, C = 1, and gamma = 0.01 achieved the highest accuracy of 99.33% in classifying the three types of coffee beans. The system was implemented as a web-based application using the Flask framework to allow users to classify coffee types in real time. This study demonstrates that the combination of HSV, PCA, and SVM is effective for visual classification of coffee beans and holds potential for industrial applications to enhance product quality consistency.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Sari, Anggraini Puspita	NIDN0716088605	anggraini.puspita.if@upnjatim.ac.id
Thesis advisor	Maulana, Hendra	NIDN1423128301	hendra.maulana.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General) > T385 Computer Graphics

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Raisah Nurul Faridah

Date Deposited:

19 Jun 2025 04:09

Last Modified:

19 Jun 2025 04:09

URI:

https://repository.upnjatim.ac.id/id/eprint/38611