Image Quality Assessment Metrics Combining Structural Similarity and Image Fidelity with Visual Attention

Image quality assessment has a great importance in several image processing applications. Recently, various objective image quality metrics have been proposed in order to predict human visual perception. In this paper, novel image quality metrics, S-SSIM (saliency-based structural similarity index) and S-VIF (saliency-based visual information fidelity), are proposed based on a visual attention model extracting frequency-tuned salient region. Saliency maps are produced from the color and luminance features of the image. SSIM and VIF in pixel domain are modified by the weighting factors of the saliency maps. We validated our approach using 2 image databases as test bed: These databases contain subjective scores for each image. Our results showed that our technique is more correlated with human subjective perception.

Görüntülenme
1
22.03.2024 tarihinden bu yana
İndirme
1
22.03.2024 tarihinden bu yana
Son Erişim Tarihi
05 Nisan 2024 12:05
Google Kontrol
Tıklayınız
Tam Metin
Tam Metin İndirmek için tıklayın Ön izleme
Detaylı Görünüm
Eser Adı
(dc.title)
Image Quality Assessment Metrics Combining Structural Similarity and Image Fidelity with Visual Attention
Yayın Türü
(dc.type)
Makale
Yazar/lar
(dc.contributor.author)
MENDİ, Engin
Atıf Dizini
(dc.source.database)
Wos
Atıf Dizini
(dc.source.database)
Scopus
Konu Başlıkları
(dc.subject)
Image Quality Assessment
Konu Başlıkları
(dc.subject)
Visual Attention
Konu Başlıkları
(dc.subject)
Saliency Maps
Konu Başlıkları
(dc.subject)
Structural Similarity
Konu Başlıkları
(dc.subject)
Visual Information Fidelity
Yayın Tarihi
(dc.date.issued)
2015
Kayıt Giriş Tarihi
(dc.date.accessioned)
2019-07-10T13:25:58Z
Açık Erişim tarihi
(dc.date.available)
2019-07-10T13:25:58Z
Özet
(dc.description.abstract)
Image quality assessment has a great importance in several image processing applications. Recently, various objective image quality metrics have been proposed in order to predict human visual perception. In this paper, novel image quality metrics, S-SSIM (saliency-based structural similarity index) and S-VIF (saliency-based visual information fidelity), are proposed based on a visual attention model extracting frequency-tuned salient region. Saliency maps are produced from the color and luminance features of the image. SSIM and VIF in pixel domain are modified by the weighting factors of the saliency maps. We validated our approach using 2 image databases as test bed: These databases contain subjective scores for each image. Our results showed that our technique is more correlated with human subjective perception.
Tek Biçim Adres
(dc.identifier.uri)
https://hdl.handle.net/20.500.12498/1172
Analizler
Yayın Görüntülenme
Yayın Görüntülenme
Erişilen ülkeler
Erişilen şehirler
6698 sayılı Kişisel Verilerin Korunması Kanunu kapsamında yükümlülüklerimiz ve cerez politikamız hakkında bilgi sahibi olmak için alttaki bağlantıyı kullanabilirsiniz.
Tamam

creativecommons
Bu site altında yer alan tüm kaynaklar Creative Commons Alıntı-GayriTicari-Türetilemez 4.0 Uluslararası Lisansı ile lisanslanmıştır.
Platforms