Paper Info
Title
Selective Super-Resolution for Scene Text Images
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.
Year
DOI
Venue
2019
10.1109/ICDAR.2019.00071
2019 International Conference on Document Analysis and Recognition (ICDAR)
Keywords
Field
DocType
Super-Resolution, Scene Text, Super-Resolution Convolutional Neural Network, Context-wise Network Fusion
Computer vision,Pattern recognition,Convolutional neural network,Computer science,Canonical correlation,Qualitative Evaluations,Correlation,Data type,Artificial intelligence,Super resolution convolutional neural network,Superresolution
Conference
ISSN
ISBN
Citations 
1520-5363
978-1-7281-3015-6
0
PageRank 
References 
Authors
0.34
10
3
Name
Order
Citations
PageRank
Ryo Nakao100.34
Brian Kenji Iwana276.58
Seiichi Uchida3790105.59