Analisis Perbandingan MobileNetV2 dan ResNet50 Berbasis Transfer Learning untuk Klasifikasi Citra dan Implementasi Text-to-Speech
DOI:
https://doi.org/10.31599/122k7c76Keywords:
Transfer Learning, MobileNetV2, ResNet50, Image Classification, Text-to-SpeechAbstract
Visual impairment limits the ability of people with blindness to recognize surrounding objects, creating the need for artificial intelligence-based assistive technology. This study compared the performance of MobileNetV2 and ResNet50 based on Transfer Learning for image classification and implemented the best web-based model integrated with Text-to-Speech. The research employed the Cross-Industry Standard Process for Data Mining methodology using the CIFAR 100 dataset. The results showed that ResNet50 achieved the highest accuracy of 79.95%, while MobileNetV2 demonstrated better computational efficiency. ResNet50 was successfully implemented in a web application capable of recognizing objects from external images and delivering the classification results through speech output.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mega Gloria, Mujiono Sadikin, Khairunnisa Fadhilla Ramdhania
This work is licensed under a Creative Commons Attribution 4.0 International License.
Please read and understand the copyright terms for submissions to this journal.
Copyright Notice
The Jurnal Keamanan Nasional is under the Creative Commons Attribution 4.0 International (CC-BY 4.0) License, according to which:
1) Authors retain copyright and grant the journal the right to first publication, with the work simultaneously licensed under the Creative Commons Attribution (CC-BY 4.0) that allows the sharing of articles published with the acknowledgement of authorship and the initial publication in this journal.
2) The authors are authorized to make additional contracts separately for distribution of the version of the work published in this journal (for example, publication in an institutional repository or as a chapter of the book), as long as there is recognition of authorship and initial publication in this journal.
3) Authors are authorized and encouraged to publish and distribute their work online (for example, in institutional repositories or on their personal pages) at any time before or during the editorial process, as it increases the impact and reference of the published work.
2.jpg)
_-_Copy1.jpg)
