Visual re-ranking with natural language understanding for text spotting

Cita com:
hdl:2117/179902
Document typeConference lecture
Defense date2018
Rights accessOpen Access
European Commission's projectHUMOUR - HUman behavioral Modeling for enhancing learning by Optimizing hUman-Robot interaction (EC-FP7-231724)
Abstract
Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to fill the gap between language and vision. We propose a post processing approach to improve scene text recognition accuracy by using occurrence probabilities of words (unigram language model), and the semantic correlation between scene and text. For this, we initially rely on an off-the-shelf deep neural network, already trained with large amount of data, which provides a series of text hypotheses per input image. These hypotheses are then re-ranked using word frequencies and semantic relatedness with objects or scenes in the image. As a result of this combination, the performance of the original network is boosted with almost no additional cost. We validate our approach on ICDAR'17 dataset.
Description
The final publication is available at link.springer.com
CitationSabir, A.; Moreno-Noguer, F.; Padro, L. Visual re-ranking with natural language understanding for text spotting. A: Asian Conference on Computer Vision. "Proceedings of the 14th Asian Conference on Computer Vision". 2018, p. 68-82.
Publisher versionhttps://link.springer.com/chapter/10.1007%2F978-3-030-20893-6_5
Collections
- IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [463]
- GPLN - Grup de Processament del Llenguatge Natural - Ponències/Comunicacions de congressos [187]
- Departament de Ciències de la Computació - Ponències/Comunicacions de congressos [1.121]
- ROBiri - Grup de Robòtica de l'IRI - Ponències/Comunicacions de congressos [181]
Files | Description | Size | Format | View |
---|---|---|---|---|
ACCV18_Submissi ... l_Semantic_Information.pdf | 1,851Mb | View/Open |
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder