Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

Handle URI:
http://hdl.handle.net/10754/622213
Title:
Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs
Authors:
Xiao, Lei; Wang, Jue; Heidrich, Wolfgang ( 0000-0002-4227-8508 ) ; Hirsch, Michael
Abstract:
Photographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of high-order filters to facilitate joint recovery of blur kernel and latent image. With extensive experiments, we show that our method produces high quality results and is highly efficient at the same time, making it a practical choice for deblurring high resolution text images captured by modern mobile devices. © Springer International Publishing AG 2016.
KAUST Department:
KAUST, Thuwal, Saudi Arabia
Citation:
Xiao L, Wang J, Heidrich W, Hirsch M (2016) Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs. Lecture Notes in Computer Science: 734–749. Available: http://dx.doi.org/10.1007/978-3-319-46487-9_45.
Publisher:
Springer Nature
Journal:
Lecture Notes in Computer Science
Issue Date:
16-Sep-2016
DOI:
10.1007/978-3-319-46487-9_45
Type:
Book Chapter
ISSN:
0302-9743; 1611-3349
Sponsors:
This work was supported in part by Adobe and Baseline Funding of KAUST. Part of this work was done when the first author was an intern at Adobe Research. The authors thank the anonymous reviewers for helpful suggestions.
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-319-46487-9_45
Appears in Collections:
Book Chapters

Full metadata record

DC FieldValue Language
dc.contributor.authorXiao, Leien
dc.contributor.authorWang, Jueen
dc.contributor.authorHeidrich, Wolfgangen
dc.contributor.authorHirsch, Michaelen
dc.date.accessioned2017-01-02T08:42:38Z-
dc.date.available2017-01-02T08:42:38Z-
dc.date.issued2016-09-16en
dc.identifier.citationXiao L, Wang J, Heidrich W, Hirsch M (2016) Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs. Lecture Notes in Computer Science: 734–749. Available: http://dx.doi.org/10.1007/978-3-319-46487-9_45.en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.doi10.1007/978-3-319-46487-9_45en
dc.identifier.urihttp://hdl.handle.net/10754/622213-
dc.description.abstractPhotographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of high-order filters to facilitate joint recovery of blur kernel and latent image. With extensive experiments, we show that our method produces high quality results and is highly efficient at the same time, making it a practical choice for deblurring high resolution text images captured by modern mobile devices. © Springer International Publishing AG 2016.en
dc.description.sponsorshipThis work was supported in part by Adobe and Baseline Funding of KAUST. Part of this work was done when the first author was an intern at Adobe Research. The authors thank the anonymous reviewers for helpful suggestions.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-46487-9_45en
dc.subjectBlind deblurringen
dc.subjectCamera motionen
dc.subjectHigh-order filtersen
dc.subjectText documenten
dc.titleLearning High-Order Filters for Efficient Blind Deconvolution of Document Photographsen
dc.typeBook Chapteren
dc.contributor.departmentKAUST, Thuwal, Saudi Arabiaen
dc.identifier.journalLecture Notes in Computer Scienceen
dc.contributor.institutionUniversity of British Columbia, Vancouver, Canadaen
dc.contributor.institutionAdobe Research, Seattle, United Statesen
dc.contributor.institutionMPI for Intelligent Systems, Tübingen, Germanyen
kaust.authorXiao, Leien
kaust.authorHeidrich, Wolfgangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.