Sistem Klasifikasi Biji Kacang Hijau (Vigna Radiata) Berbasis Image Processing Menggunakan Metode CNN-PSO

Bagus Arianto, Ramadhani Anandhitya (2026) Sistem Klasifikasi Biji Kacang Hijau (Vigna Radiata) Berbasis Image Processing Menggunakan Metode CNN-PSO. Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 2042221045-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Klasifikasi biji kacang hijau secara manual cenderung memerlukan waktu lama dan menghasilkan penilaian yang tidak selalu konsisten. Penelitian ini mengembangkan alat handheld berbasis image processing untuk mengklasifikasikan kualitas biji kacang hijau ke dalam dua kelas, yaitu Good dan Bad, menggunakan metode Convolutional Neural Network (CNN) yang dioptimasi dengan algoritma Particle Swarm Optimization (PSO). Sistem dilengkapi dengan kamera, pencahayaan LED, tray grid dengan pengaturan Region of Interest (ROI), serta antarmuka pengguna (Human–Machine Interface) untuk menampilkan hasil klasifikasi secara real-time. Dataset yang digunakan berjumlah 1.530 citra, dan pengujian dilakukan pada beberapa skenario dengan variasi warna tray dan komposisi sampel. Evaluasi performa menggunakan metrik precision, recall, F1-score, akurasi, dan confusion matrix. Hasil pengujian menunjukkan bahwa CNN-PSO memberikan performa lebih baik dibandingkan CNN baseline, dengan nilai F1-score sebesar 0.93, akurasi 0.90, dan waktu proses rata-rata 10 detik. Peningkatan performa juga terlihat dari naiknya jumlah True Positive dan menurunnya False Negative, yang menunjukkan bahwa optimasi PSO mampu meningkatkan akurasi dan efisiensi sistem klasifikasi biji kacang hijau secara non-destruktif.
===========================================================================================================================================
Manual classification of mung beans tends to be time-consuming and produces inconsistent results. This study developed a handheld image processing tool to classify the quality of mung beans into two classes, Good and Bad, using a Convolutional Neural Network (CNN) method optimized with a Particle Swarm Optimization (PSO) algorithm. The system is equipped with a camera, LED lighting, a grid tray with Region of Interest (ROI) settings, and a user interface (Human–Machine Interface) to display classification results in real-time. The dataset used consisted of 1,530 images, and testing was conducted in several scenarios with variations in tray color and sample composition. Performance evaluation used precision, recall, F1-score, Accuracy, and confusion matrix metrics. The test results showed that CNN-PSO performed better than the baseline CNN, with an F1-score of 0.93, Accuracy of 0.90, and an average processing time of 10 seconds. The improvement in performance was also evident from the increase in the number of True Positives and the decrease in False Negatives, indicating that PSO optimization was able to improve the Accuracy and efficiency of the non-destructive mung bean classification system.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Convolutional Neural Network (CNN), GUI Python, Image Processing, Kacang Hijau, Klasifikasi Benih, Particle Swarm Optimization (PSO), Sistem Klasifikasi Citra ====================================================================================================================================== Convolutional Neural Network (CNN), GUI Python, Image Processing, Mung Bean, Particle Swarm Optimization (PSO), Seed Classification, Visual Classification System
Subjects:	S Agriculture > SB Plant culture S Agriculture > SB Plant culture > SB409.58 Plant propagation. Including in vitro propagation T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.62 Decision support systems T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing. T Technology > TA Engineering (General). Civil engineering (General) > TA174 Computer-aided design. T Technology > TA Engineering (General). Civil engineering (General) > TA593.35 Instruments, cameras, etc. T Technology > TR Photography > TR260.7 Autofocus cameras
Divisions:	Faculty of Vocational > Instrumentation Engineering
Depositing User:	Ramadhani Anandhitya Bagus Arianto
Date Deposited:	31 Jul 2026 03:06
Last Modified:	31 Jul 2026 03:06
URI:	http://repository.its.ac.id/id/eprint/140866

Actions (login required)

View Item