Título
Rectification and Super-Resolution Enhancements for Forensic Text Recognition
Autor
Facultad/Centro
Área de conocimiento
Título de la revista
Sensors
Número de la revista
20
Datos de la obra
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 (Switzerland), 20(20), 1-17. https://doi.org/10.3390/S20205850
Editor
MDPI
Fecha
2020-10-16
Resumo
[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.
Materia
Palabras clave
Idioma
eng
Tipo documental
info:eu-repo/semantics/article
Peer review
SI
URI
DOI
Versión del editor
https://www.mdpi.com/1424-8220/20/20/5850
Aparece en las colecciones
- Untitled [5567]
Arquivos deste item
Tamaño:
5.505Mb
Formato:
Adobe PDF
Descripción:
Artículo publicado