Classification of Original and Fake Images Using Deep Learning- Resnet50

DOI

10.2991/978-94-6463-413-6_6How to use a DOI?

Keywords

Classification Image; Convolution Neural Network; ResNet50

Abstract

Computer Vision has developed and become a necessity for human life. Computer Vision is widely used in image classification tasks, object detection, semantic segmentation, video understanding, and so on. In this research, Computer Vision is used to perform classification tasks to distinguish between real and fake images of human faces. To carry out classification tasks, this research will use a CNN model with the ResNet50 architecture which is known to be good at carrying out image classification tasks. ResNet50 is well known to solve the vanishing gradient problem with fewer stacked layers and minimizes time in learning with ever-increasing accuracy. This research uses 589 real human face image data and 700 fake human face data. By using image augmentation in the pre-processing stage, the data is divided by 80% for training data and 20% for validation data. The results of model training on training data show an accuracy of 76,07% and the model performance in testing data shows an accuracy of 53%.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Novita Rajagukguk
AU  - I Putu Eka Nila Kencana
AU  - I G. N. Lanang Wijaya Kusuma
PY  - 2024
DA  - 2024/05/13
TI  - Classification of Original and Fake Images Using Deep Learning- Resnet50
BT  - Proceedings of the First International Conference on Applied Mathematics, Statistics, and Computing (ICAMSAC 2023)
PB  - Atlantis Press
SP  - 51
EP  - 61
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-413-6_6
DO  - 10.2991/978-94-6463-413-6_6
ID  - Rajagukguk2024
ER  -