Compartir
Título
Enhancing text recognition on Tor Darknet images
Autor
Facultad/Centro
Área de conocimiento
Es parte de
XL Jornadas de Automática: libro de actas. Ferrol, 4-6 de septiembre de 2019
Cita Bibliográfica
Blanco Medina, P., Fidalgo Fernández, E., Alegre Gutiérrez, E., Wesam Al Nabki, M., & Chaves Sánchez, D. (2019). Enhancing text recognition on Tor Darknet images. En J. L. Calvo Rolle, J.-L. Casteleiro-Roca, I. Fernández-Ibáñez, Ó. Fontenla Romero, E. Jove Pérez, A. J. Leira-Rejas, J. A. López Vázquez, V. Loureiro-Vázquez, M.-C. Meizoso-López, F. J. Pérez Castelo, A. J. Piñón Pazos, H. Quintián Pardo, J. M. Rivas Rodríguez, B. A. Rodríguez Gómez, & R. A. Vega-Vega (eds.), XL Jornadas de Automática: libro de actas. Ferrol, 4-6 de septiembre de 2019.
Editorial
Universidade da Coruña
Fecha
2019
Resumen
[EN] ext Spotting can be used as an approach to retrieve information found in images that cannot be obtained otherwise, by performing text detection rst and then recognizing the located text. Examples of images to apply this task on can be found in Tor network images, which contain information that may not be found in plain text. When comparing both stages, the latter performs worse due to the low resolution of the cropped areas among other problems. Focusing on the recognition part of the pipeline, we study the performance of ve recognition approaches, based on state-ofthe- art neural network models, standalone OCR, and OCR enhancements. We complement them using string-matching techniques with two lexicons and compare computational time on ve di erent datasets, including Tor network images. Our nal proposal achieved 39,70% precision of text recognition in a custom dataset of images taken from Tor domains
Materia
Palabras clave
URI
Aparece en las colecciones
- Capítulos de monografías [1541]
Ficheros en el ítem
Tamaño:
3.875
xmlui.dri2xhtml.METS-1.0.size-megabytes
Formato:
Adobe PDF
Descripción:
Aportación congreso