Dual-Stream Complex-Valued Convolutional Network for Authentic Dehazed Image Quality Assessment

Dual-Stream Complex-Valued Convolutional Network for Authentic Dehazed Image Quality Assessment

Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employe...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 33(2024) vom: 09., Seite 466-478
1. Verfasser: Guan, Tuxin (VerfasserIn)
Weitere Verfasser: Li, Chaofeng, Zheng, Yuhui, Wu, Xiaojun, Bovik, Alan C
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM366409964
003 DE-627
005 20240114233107.0
007 cr uuu---uuuuu
008 231229s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2023.3343029  |2 doi 
028 5 2 |a pubmed24n1253.xml 
035 |a (DE-627)NLM366409964 
035 |a (NLM)38150345 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Guan, Tuxin  |e verfasserin  |4 aut 
245 1 0 |a Dual-Stream Complex-Valued Convolutional Network for Authentic Dehazed Image Quality Assessment 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 08.01.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employed that exploits the advantages of complex-valued representations, achieving better generalization capability on perceptual feature learning than real-valued ones. To learn more discriminative features to analyze the perceptual quality of dehazed images, we design a dual-stream CV-CNN architecture. The dual-stream model comprises a distortion-sensitive stream that operates on the dehazed RGB image, and a haze-aware stream on a novel dark channel difference image. The distortion-sensitive stream accounts for perceptual distortion artifacts, while the haze-aware stream addresses the possible presence of residual haze. Experimental results on three publicly available dehazed image quality assessment (DQA) databases demonstrate the effectiveness and generalization of our proposed CV-CNN DQA model as compared to state-of-the-art no-reference image quality assessment algorithms 
650 4 |a Journal Article 
700 1 |a Li, Chaofeng  |e verfasserin  |4 aut 
700 1 |a Zheng, Yuhui  |e verfasserin  |4 aut 
700 1 |a Wu, Xiaojun  |e verfasserin  |4 aut 
700 1 |a Bovik, Alan C  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 33(2024) vom: 09., Seite 466-478  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:33  |g year:2024  |g day:09  |g pages:466-478 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2023.3343029  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 33  |j 2024  |b 09  |h 466-478