Efficient document-image super-resolution using convolutional neural network

DOI10.1007/S12046-018-0794-1MaRDI QIDQ724653zbMATH OpenOpenAlexWikidataFDO

Authors Ram K. Pandey, A. G. Ramakrishnan

Publication date 26 July 2018

Published in Sādhanā (Search for Journal in Brave)

Full work available at URL https://www.ias.ac.in/describe/article/sadh/043/02/0015

zbMATH Keywords

document imagesuper-resolutionspatial resolutionPSNRconvolutional neural networkdocument qualityOCRrecognition accuracy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• Image super-resolution based on recursive residual networks
• Residual learning of deep CNN for image super-resolution
• Image super-resolution based on deep learning features
• Remote sensing image super-resolution reconstruction based on deep convolution neural network
• Image super-resolution based on deep network with hierarchical feature maps

Cites work

• scientific article; zbMATH DE number 1930905 (Why is no real title available?)
• scientific article; zbMATH DE number 1930907 (Why is no real title available?)
• Coupled Dictionary Training for Image Super-Resolution
• GitHub
• Image Super-Resolution Via Sparse Representation
• Tesseract

Cited in

(1)

• Impact of low resolution on image recognition with deep neural networks: an experimental study

Describes a project that uses

Uses Software

• Theano
• Keras
• GitHub
• Tesseract

This page was built for publication: Efficient document-image super-resolution using convolutional neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q724653)