Rectification and Super-Resolution Enhancements for Forensic Text Recognition

[EN] 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, wh...

Descripción completa

Detalles Bibliográficos
Autores: Blanco Medina, Pablo, Fidalgo Fernández, Eduardo, Alegre Gutiérrez, Enrique, Alaiz Rodríguez, Rocío, Jáñez Martino, Francisco, Bonnici, Alexandra
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:Universidad de León
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:buleria.unileon.es:10612/20387
Acceso en línea:https://www.mdpi.com/1424-8220/20/20/5850
https://hdl.handle.net/10612/20387
Access Level:acceso abierto
Palabra clave:Cibernética
Informática
Text spotting
Text recognition
Super-resolution
Tor Darknet
Computer forensics
3304.05 Sistemas de Reconocimiento de Caracteres
1207.03 Cibernética
1203.17 Informática
Descripción
Sumario:[EN] 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.