Publication

Visual reranking with natural language understanding for text spotting

Conference Article

Conference

Asian Conference on Computer Vision (ACCV)

Edition

14th

File

Download the digital copy of the doc pdf document

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.

Categories

computer vision.

Scientific reference

A. Sabir, F. Moreno-Noguer and L. Padró. Visual reranking with natural language understanding for text spotting, 14th Asian Conference on Computer Vision, 2018, , to appear.