Identification of document paper using hybrid feature extraction
Journal of Forensic Sciences · 2023-09 · 68 (5) · 1808-1815
DOI: 10.1111/1556-4029.15330 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Forensic Sciences, online erschienen am 07.07.2023. Verfasst von Joong Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of AI and Big Data in Medicine, Yonsei University Wonju College of Medicine, Wonju-si, South Korea. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 46 Literaturangaben.
Abstract (Originalsprache)
Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray‐level co‐occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of AI and Big Data in Medicine, Yonsei University Wonju College of Medicine, Wonju-si, South Korea.
- Digital Analysis Division, National Forensic Service, Wonju-si, South Korea.
Zitieren
APA
Lee, J., Kim, H., Yook, S., & Kang, T. Y. (2023). Identification of document paper using hybrid feature extraction. Journal of Forensic Sciences, 68(5), 1808-1815. https://doi.org/10.1111/1556-4029.15330
Vancouver
Lee J, Kim H, Yook S, Kang TY. Identification of document paper using hybrid feature extraction. Journal of Forensic Sciences. 2023;68(5):1808-1815. doi:10.1111/1556-4029.15330
BibTeX
@article{Lee2023,
author = {Lee, Joong and Kim, Hongseok and Yook, Simyub and Kang, Tae-Yi},
title = {Identification of document paper using hybrid feature extraction},
journal = {Journal of Forensic Sciences},
year = {2023},
volume = {68},
number = {5},
pages = {1808--1815},
doi = {10.1111/1556-4029.15330}
}
EUVIMED