TY - GEN
T1 - Tempered Image Detection Using ELA and Convolutional Neural Networks
AU - Mishra, Anupama
AU - Kong, Kwok Tai Chui Hong
AU - Gupta, Brij B.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Images are often manipulated to benefit one party, serving as crucial evidence. This manipulation, often used in fake news or misleading information, frequently involves image falsification. Detecting such falsification requires a robust model capable of processing vast image data efficiently. In today's data-rich era, Deep Learning, especially the use of Convolutional Neural Networks with Error Level Analysis, has achieved an impressive 87.75% accuracy and convergence in 10 epochs for detecting forged images.
AB - Images are often manipulated to benefit one party, serving as crucial evidence. This manipulation, often used in fake news or misleading information, frequently involves image falsification. Detecting such falsification requires a robust model capable of processing vast image data efficiently. In today's data-rich era, Deep Learning, especially the use of Convolutional Neural Networks with Error Level Analysis, has achieved an impressive 87.75% accuracy and convergence in 10 epochs for detecting forged images.
KW - CNN
KW - ELA
KW - Fake Image
UR - http://www.scopus.com/inward/record.url?scp=85187020543&partnerID=8YFLogxK
U2 - 10.1109/ICCE59016.2024.10444440
DO - 10.1109/ICCE59016.2024.10444440
M3 - Conference contribution
AN - SCOPUS:85187020543
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
BT - 2024 IEEE International Conference on Consumer Electronics, ICCE 2024
T2 - 2024 IEEE International Conference on Consumer Electronics, ICCE 2024
Y2 - 6 January 2024 through 8 January 2024
ER -