Hallucinating Very Low Resolution Face Images to 16x magnification with Age based Attributes 연령기반 속성을 이용한 초저화질 얼굴 이미지 16배 복원

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 442
  • Download : 116
DC FieldValueLanguage
dc.contributor.authorKim, Jihwanko
dc.contributor.authorChoi, Sungheeko
dc.date.accessioned2021-02-03T09:10:25Z-
dc.date.available2021-02-03T09:10:25Z-
dc.date.created2020-11-09-
dc.date.created2020-11-09-
dc.date.issued2020-06-
dc.identifier.citationJournal of WSCG, v.28, no.1-2, pp.57 - 63-
dc.identifier.issn1213-6972-
dc.identifier.urihttp://hdl.handle.net/10203/280533-
dc.description.abstractFace hallucination is a type of super resolution that restores very low resolution (8 × 8 pixel) to high resolution (128×128 pixel) face images. Since unique facial features caused by age, e.g.wrinkles, are ignored during restoration, restored face images can be somewhat dissimilar to the original faces, particularly for older people. To solve this problem, we construct a pipeline network to restore face images more realistically by including age attribute, predicted from the low resolution image. Predicted age attribute is divided into young and old groups, where the aging network is the last pipeline stage and only applied when the original face image includes old age attributes. Thus, older people tend to be restored with wrinkles and features similar to their original appearance. Restored images are compared qualitatively and quantitatively with images created by existing methods. We show that the proposed method maintains and restores age related personality features, such as wrinkles, producing higher structural similarity index than other methods. © 2020, Vaclav Skala Union Agency. All rights reserved.-
dc.languageEnglish-
dc.publisherUniversity of West Bohemia-
dc.titleHallucinating Very Low Resolution Face Images to 16x magnification with Age based Attributes-
dc.title.alternative연령기반 속성을 이용한 초저화질 얼굴 이미지 16배 복원-
dc.typeArticle-
dc.identifier.scopusid2-s2.0-85090683639-
dc.type.rimsART-
dc.citation.volume28-
dc.citation.issue1-2-
dc.citation.beginningpage57-
dc.citation.endingpage63-
dc.citation.publicationnameJournal of WSCG-
dc.identifier.doi10.24132/jwscg.2020.28.7-
dc.contributor.localauthorChoi, Sunghee-
dc.contributor.nonIdAuthorKim, Jihwan-
dc.description.isOpenAccessY-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorAge-
dc.subject.keywordAuthorDeep learning-
dc.subject.keywordAuthorFace hallucination-
dc.subject.keywordAuthorPersonality-
dc.subject.keywordAuthorPipeline network-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
116603.pdf(3.97 MB)Download

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0