Mobile QR Code
Title Forgery Detection and Characteristic Analysis of Scanned Document Utilizing Paper Fingerprint
Authors 최용수(YongSoo CHOI)
DOI https://doi.org/10.5573/ieie.2026.63.8.53
Page pp.53-58
ISSN 2287-5026
Keywords Forgery; Scanned document; ELA(Error Level Analysis); Compression
Abstract With the rapid growth of digital images and documents, the problem of forgery and manipulation has become a significant issue affecting social trust. In particular, the widespread use of social media and online platforms has accelerated the distribution of tampered images, increasing the demand for automated detection technologies. Scanned documents, which are stored as image-based data, retain subtle compression artifacts when alterations occur. In this study, we propose a forgery detection method for scanned documents based on Error Level Analysis (ELA), combined with block structure analysis to enhance detection efficiency. The proposed approach analyzes localized compression inconsistencies by dividing the image into structured blocks, enabling more precise identification of manipulated regions. Experimental results demonstrate that the proposed method achieves improved detection accuracy(90.5%), precision(88.7%) and recall(87.9%) rate compared to conventional ELA-based approaches. These findings suggest that the proposed technique can be effectively applied to practical forgery detection systems in the field of digital forensics.