Image of KLASIFIKASI CITRA KUE TRADISIONAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Text

KLASIFIKASI CITRA KUE TRADISIONAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Traditional cake image classification aims to recognize various types of cakes based on visual features, thereby assisting in the effort to introduce traditional cakes. Indonesian traditional cakes hold significant cultural value that must be preserved while also presenting substantial potential in supporting tourism through culinary tourism. This study develops a classification model based on Convolutional Neural Networks (CNN) to identify eight types of Indonesian traditional cakes namely Dadar Gulung, Kastengel, Klepon, Lapis, Lumpur, Risoles, Serabi, and Putri Salju. The dataset was sourced from Kaggle and further enriched by utilizing the Google Custom Search API. The research stages included image preprocessing such as cropping and resizing, splitting the dataset into training (70%), validation (15%), and testing (15%) sets, and augmenting the data to increase variability. The model was trained using two CNN architectures, Xception and VGG-19, with 24 fine-tuning scenarios involving various combinations of batch size, learning rate, and layer settings. The results showed that Xception outperformed VGG-19 in all metrics. Xception achieved the best performance with a configuration of unfreezing layers, a learning rate of 0,0001, and a batch size of 64, resulting in an accuracy of 97,38%, precision of 97,4%, recall of 97,38%, and F1-score of 97,38%. Meanwhile, VGG- 19 achieved its best performance with unfrozen layers, a learning rate of 0.00001, and a batch size of 32, yielding 96.46% accuracy, 96.48% precision, 96.46% recall, and 96.44% F1-score.

Availability
Inventory Code Barcode Call Number Location Status
2507001924T169996T1699962025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1699962025
Publisher
: Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
x, 96 hlm.; ill.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
004.07
Content Type
-
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Teknik Informatika
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment