Cited 0 time in webofscience Cited 0 time in scopus

Facial Image Super-Resolution Reconstruction Based on Separated Frequency Components

Title
Facial Image Super-Resolution Reconstruction Based on Separated Frequency Components
Authors
Kim, H[Kim, Hyunduk]Lee, SH[Lee, Sang-Heon]Sohn, MK[Sohn, Myoung-Kyu]Kim, DJ[Kim, Dong-Ju]Kim, B[Kim, Byungmin]
DGIST Authors
Kim, H[Kim, Hyunduk]; Lee, SH[Lee, Sang-Heon]; Sohn, MK[Sohn, Myoung-Kyu]; Kim, DJ[Kim, Dong-Ju]; Kim, B[Kim, Byungmin]
Issue Date
2013-06
Citation
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, E96A(6), 1315-1322
Type
Article
Article Type
Article
Keywords
AlgorithmsBilateral FilterBilateral FiltersFacial Super ResolutionFrequency DomainFrequency DomainsImage ReconstructionRegularization TechniqueSeparationSparse RepresentationSuper Resolution
ISSN
0916-8508
Abstract
Super resolution (SR) reconstruction is the process of fusing a sequence of low-resolution images into one high-resolution image. Many researchers have introduced various SR reconstruction methods. However, these traditional methods are limited in the extent to which they allow recovery of high-frequency information. Moreover, due to the selfsimilarity of face images, most of the facial SR algorithms are machine learning based. In this paper, we introduce a facial SR algorithm that combines learning-based and regularized SR image reconstruction algorithms. Our conception involves two main ideas. First, we employ separated frequency components to reconstruct high-resolution images. In addition, we separate the region of the training face image. These approaches can help to recover high-frequency information. In our experiments, we demonstrate the effectiveness of these ideas. Copyright © 2013 The Institute of Electronics, Information and Communication Engineers.
URI
http://hdl.handle.net/20.500.11750/3232
DOI
10.1587/transfun.E96.A.1315
Publisher
Institute of Electronics, Information and Communication Engineers
Related Researcher
Files:
There are no files associated with this item.
Collection:
ETC1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE