Selective super-resolution for scene text images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we realize the enhancement of super-resolution using images with scene text. Specifically, this paper proposes the use of Super-Resolution Convolutional Neural Networks (SRCNN) which are constructed to tackle issues associated with characters and text. We demonstrate that standard SRCNNs trained for general object super-resolution is not sufficient and that the proposed method is a viable method in creating a robust model for text. To do so, we analyze the characteristics of SRCNNs through quantitative and qualitative evaluations with scene text data. In addition, analysis using the correlation between layers by Singular Vector Canonical Correlation Analysis (SVCCA) and comparison of filters of each SRCNN using t-SNE is performed. Furthermore, in order to create a unified super-resolution model specialized for both text and objects, a model using SRCNNs trained with the different data types and Content-wise Network Fusion (CNF) is used. We integrate the SRCNN trained for character images and then SRCNN trained for general object images, and verify the accuracy improvement of scene images which include text. We also examine how each SRCNN affects super-resolution images after fusion.

Original languageEnglish
Title of host publicationProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
PublisherIEEE Computer Society
Pages401-406
Number of pages6
ISBN (Electronic)9781728128610
DOIs
Publication statusPublished - Sep 2019
Event15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australia
Duration: Sep 20 2019Sep 25 2019

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363

Conference

Conference15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
CountryAustralia
CitySydney
Period9/20/199/25/19

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Selective super-resolution for scene text images'. Together they form a unique fingerprint.

Cite this