DEEP FAKE VIDEO DETECTION USING INCEPTIONRESNETV2
Alt Text: Deep Fake Video Detection Using InceptionResNetV2
Title: Deep Fake Video Detection Using InceptionResNetV2
Caption: Leveraging deep learning to detect deepfake faces in videos with high accuracy.
Description: This study presents a deep learning-based approach to detecting deepfake faces in videos using the InceptionResNetV2 model. The framework employs FaceForensics++ as a benchmark dataset, utilizing key frame extraction for efficient feature processing, achieving over 90% accuracy in distinguishing real from fake videos.
Keywords: Deepfake Detection, InceptionResNetV2, FaceForensics++, Key Frame Extraction, Video Authentication
International Journal of Engineering and Techniques – Volume 10 Issue 3, June 2024
Chinthaginjala Shalini1, Chilaka Thanuja2
1UG Student, Department of Computer Science & Engineering, Geethanjali Institute of Science and Technology, Gangavaram, Andhra Pradesh, India.
2UG Student, Department of Computer Science & Engineering, Geethanjali Institute of Science and Technology, Gangavaram, Andhra Pradesh, India.
Abstract
Deepfake technology raises concerns about the authenticity of digital media, emphasizing the need for effective detection methods. This research introduces a transparent, cost-sensitive deep learning approach using InceptionResNetV2 to identify deepfake faces in videos. FaceForensics++ serves as the benchmark dataset, with key frame extraction used for efficient feature processing. The study highlights the adaptability of the proposed model, achieving over 90% accuracy in distinguishing real from fake videos while advocating for continuous improvements as deepfake techniques evolve.
Keywords
Deepfake Detection, InceptionResNetV2, FaceForensics++, Key Frame Extraction, Video Authentication
How to Cite
Shalini, C., Thanuja, C., “Deep Fake Video Detection Using InceptionResNetV2,” International Journal of Engineering and Techniques, Volume 10, Issue 3, June 2024. ISSN 2395-1303
Post Comment