Skripsi

KLASIFIKASI CITRA MAKANAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARISTEKTUR EFFNET

---

This study develops a food image classification system for Indonesian traditional dishes based on Convolutional Neural Network to support the digitalization of internal processes in the culinary sector, particularly for automatic food identification and menu management. The model is built using the EfficientNet family and evaluated on a dataset consisting of 30 classes of Indonesian traditional foods with high visual diversity. The training process includes data cleansing, image preprocessing, data augmentation, and the application of regularization strategies to improve training stability and model generalization. Experimental results show that EfficientNetV2-S achieves the best performance, with a test accuracy of 97.17%, accompanied by consistent predictions based on confusion matrix analysis and evaluation metrics. These results indicate that the proposed system is capable of accurately and consistently classifying Indonesian food images, demonstrating its potential application as a digital solution for automatic menu identification in the Indonesian culinary industry.

---

Availability

Detail Information

Series Title

-

Call Number

T1897982025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 149 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.420 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Pengenalan Citra Makanan

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment