Rectification and Super-Resolution Enhancements for Forensic Text Recognition †
1
Department of Electrical, Systems and Automation, Universidad de León, 24007 León, Spain
2
INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain
3
Faculty of Engineering, University of Malta, MSD2080 Msida, Malta
*
Author to whom correspondence should be addressed.
†
This paper is an extended version of our paper published in Blanco-Medina, P.; Fidalgo, E.; Alegre, E.; Jánez-Martino, F. Improving Text Recognition in Tor darknet with Rectification and Super-Resolution techniques. In Proceedings of the 9th International Conference on Imaging for Crime Detection and Prevention (ICDP-2019), London, UK, 2019; pp. 32–37.
Sensors 2020, 20(20), 5850; https://doi.org/10.3390/s20205850
Received: 27 July 2020
/
Revised: 6 October 2020
/
Accepted: 11 October 2020
/
Published: 16 October 2020
(This article belongs to the Special Issue Selected Papers from the 9th International Conference on Imaging for Crime Detection and Prevention (ICDP-19))
Retrieving text embedded within images is a challenging task in real-world settings. Multiple problems such as low-resolution and the orientation of the text can hinder the extraction of information. These problems are common in environments such as Tor Darknet and Child Sexual Abuse images, where text extraction is crucial in the prevention of illegal activities. In this work, we evaluate eight text recognizers and, to increase the performance of text transcription, we combine these recognizers with rectification networks and super-resolution algorithms. We test our approach on four state-of-the-art and two custom datasets (TOICO-1K and Child Sexual Abuse (CSA)-text, based on text retrieved from Tor Darknet and Child Sexual Exploitation Material, respectively). We obtained a 0.3170 score of correctly recognized words in the TOICO-1K dataset when we combined Deep Convolutional Neural Networks (CNN) and rectification-based recognizers. For the CSA-text dataset, applying resolution enhancements achieved a final score of 0.6960. The highest performance increase was achieved on the ICDAR 2015 dataset, with an improvement of 4.83% when combining the MORAN recognizer and the Residual Dense resolution approach. We conclude that rectification outperforms super-resolution when applied separately, while their combination achieves the best average improvements in the chosen datasets.
View Full-Text
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
-
Externally hosted supplementary file 1
Doi: 10.1049/cp.2019.1164
Description: Conference Proceeding
MDPI and ACS Style
Blanco-Medina, P.; Fidalgo, E.; Alegre, E.; Alaiz-Rodríguez, R.; Jáñez-Martino, F.; Bonnici, A. Rectification and Super-Resolution Enhancements for Forensic Text Recognition. Sensors 2020, 20, 5850. https://doi.org/10.3390/s20205850
AMA Style
Blanco-Medina P, Fidalgo E, Alegre E, Alaiz-Rodríguez R, Jáñez-Martino F, Bonnici A. Rectification and Super-Resolution Enhancements for Forensic Text Recognition. Sensors. 2020; 20(20):5850. https://doi.org/10.3390/s20205850
Chicago/Turabian StyleBlanco-Medina, Pablo, Eduardo Fidalgo, Enrique Alegre, Rocío Alaiz-Rodríguez, Francisco Jáñez-Martino, and Alexandra Bonnici. 2020. "Rectification and Super-Resolution Enhancements for Forensic Text Recognition" Sensors 20, no. 20: 5850. https://doi.org/10.3390/s20205850
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
