Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/127910
Title: Rectification and super-resolution enhancements for forensic text recognition
Authors: Blanco-Meding, Pablo
Fidalgo, Eduardo
Alegre, Enrique
Alaiz-Rodriguez, Rocio
Janez-Martino, Francisco
Bonnici, Alexandra
Keywords: High resolution imaging
Dark Web
Digital forensic science
Deep learning (Machine learning)
Computer crimes -- Investigation
Optical pattern recognition
Issue Date: 2020
Publisher: MDPI AG
Citation: Blanco-Medina, P., Fidalgo, E., Alegre, E., Alaiz-Rodríguez, R., Jáñez-Martino, F. & Bonnici, A. (2020). Rectification and super-resolution enhancements for forensic text recognition. Sensors, 20(20), 5850.
Abstract: 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.
URI: https://www.um.edu.mt/library/oar/handle/123456789/127910
Appears in Collections:Scholarly Works - FacEngSCE

Files in This Item:
File Description SizeFormat 
sensors-20-05850.pdf
  Restricted Access
5.64 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.