🧪 Test?View on arXiv
Visual Forensic Detection of Fabricated Bangla News Photocards using Deep Learning
Not provided
deep learningimage forgery detectioncomputer visiondata augmentation
2611.05403
Builder Relevance
2h ago80%
Abstract
The paper presents a method for detecting fabricated Bangla news photocards using deep learning techniques.
Reality Card
Core Claim
A YOLOv8n-cls model fine-tuned on a dataset of Bangla photocards achieved 97.36% accuracy in detecting fabricated images.
Method / Result
The YOLOv8n-cls model reached 97.36% +/- 0.42% accuracy.
Limitations
The compact CNNs were found to under-fit, indicating potential issues with model complexity and generalization.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.