Visual Semantic Re-ranker for Text Spotting
Abstract
Many current state-of-the-art methods for text recognition are based on purely local information and ignore the semantic correlation between text and its surrounding visual context. In this paper, we propose a post-processing approach to improve the accuracy of text spotting by using the semantic relation between the text and the scene. We initially rely on an off-the-shelf deep neural network that provides a series of text hypotheses for each input image. These text hypotheses are then re-ranked using the semantic relatedness with the object in the image. As a result of this combination, the performance of the original network is boosted with a very low computational cost. The proposed framework can be used as a drop-in complement for any text-spotting algorithm that outputs a ranking of word hypotheses. We validate our approach on ICDAR'17 shared task dataset.
Cite
@article{arxiv.1810.09776,
title = {Visual Semantic Re-ranker for Text Spotting},
author = {Ahmed Sabir and Francesc Moreno-Noguer and Lluís Padró},
journal= {arXiv preprint arXiv:1810.09776},
year = {2018}
}