RIZKIKA SITI SYIFA
Program Studi Informatika, Institut Teknologi Nasional Bandung

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Klasifikasi Citra Bibit Tanaman Menggunakan Convolutional Neural Network Dan Improved Feature Pyramid Network MUHAMMAD ICHWAN; RIZKIKA SITI SYIFA
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 8, No 1 (2023): MIND Journal
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v8i1.1-13

Abstract

AbstrakKlasifikasi bibit tanaman bertujuan untuk membantu mempermudah pengendalian jenis tanaman. Tugas klasifikasi tanaman menggunakan metode manual rentan terhadap kesalahan manusia. Pada penelitian ini, CNN dan Improved FPN diimplementasikan untuk meningkatkan akurasi pada saat melakukan tugas klasifikasi. Peningkatan FPN dilakukan untuk meningkatkan kualitas informasi yang didapatkan fitur, dengan menerapkan Channel Attention Module dan Augmented Bottom-up Pathway. Arsitektur ResNet50 digunakan sebagai backbone konvolusi FPN untuk meningkatkan kemampuan FPN mengekstraksi fitur. CNN kemudian diterapkan pada setiap peta fitur FPN akhir untuk mengklasifikasikan data. Hasil pengujian menunjukkan model memiliki kinerja lebih baik ketika FPN ditingkatkan dengan Channel Attention Module dan Augmented Bottom-up Pathway dengan rasio pengurangan Channel Attention diatur ke nilai 4 dengan akurasi pengujian yaitu 93,11% dan skor F1 yaitu 93%.Kata kunci: bibit tanaman, cnn, fpn, resnet50, channel attention module, augmented bottom-up pathway, klasifikasi citraAbstractPlant seedlings classification aims to help facilitate plant species control. The plant classification task using manual methods is prone to human error. In this study, CNN and Improved FPN were implemented to increase accuracy when performing the classification task. The FPN improvement was done to improve the quality of information obtained by the features, by implementing Channel Attention Module and Augmented Bottom-up Pathway. ResNet50 architecture was used as the convolutional backbone in FPN to enhance the feature extraction capabilities. CNN was then applied to each of FPN final feature maps to classify the data. The test results showed that the model performed better when the FPN was improved with the Channel Attention Module and Augmented Bottom-up Pathway where the Channel Attention reduction ratio was set to 4 with test accuracy of 93.11% and F1 score of 93%.Keywords: plant seedlings, cnn, fpn, resnet50, channel attention module, augmented bottom-up pathway, image classificationÂ