Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891749081> ?p ?o ?g. }
- W2891749081 endingPage "17" @default.
- W2891749081 startingPage "1" @default.
- W2891749081 abstract "In recent years, blind image quality assessment in the field of 2D image/video has gained the popularity, but its applications in 3D image/video are to be generalized. In this paper, we propose an effective blind metric evaluating stereo images via deep belief network (DBN). This method is based on wavelet transform with both 2D features from monocular images respectively as image content description and 3D features from a novel depth perception map (DPM) as depth perception description. In particular, the DPM is introduced to quantify longitudinal depth information to align with human stereo visual perception. More specifically, the 2D features are local histogram of oriented gradient (HoG) features from high frequency wavelet coefficients and global statistical features including magnitude, variance and entropy. Meanwhile, the global statistical features from the DPM are characterized as 3D features. Subsequently, considering binocular characteristics, an effective binocular weight model based on multiscale energy estimation of the left and right images is adopted to obtain the content quality. In the training and testing stages, three DBN models for the three types features separately are used to get the final score. Experimental results demonstrate that the proposed stereo image quality evaluation model has high superiority over existing methods and achieve higher consistency with subjective quality assessments." @default.
- W2891749081 created "2018-09-27" @default.
- W2891749081 creator A5013822484 @default.
- W2891749081 creator A5014654309 @default.
- W2891749081 creator A5059540876 @default.
- W2891749081 creator A5066144350 @default.
- W2891749081 creator A5068253534 @default.
- W2891749081 creator A5091485657 @default.
- W2891749081 date "2019-02-01" @default.
- W2891749081 modified "2023-10-18" @default.
- W2891749081 title "Blind assessment for stereo images considering binocular characteristics and deep perception map based on deep belief network" @default.
- W2891749081 cites W1500458919 @default.
- W2891749081 cites W1565215063 @default.
- W2891749081 cites W1644402181 @default.
- W2891749081 cites W1930650491 @default.
- W2891749081 cites W1950117310 @default.
- W2891749081 cites W1977246677 @default.
- W2891749081 cites W1978301949 @default.
- W2891749081 cites W1981076008 @default.
- W2891749081 cites W1982471090 @default.
- W2891749081 cites W2037153066 @default.
- W2891749081 cites W2046102294 @default.
- W2891749081 cites W2046119925 @default.
- W2891749081 cites W2062860282 @default.
- W2891749081 cites W2065039464 @default.
- W2891749081 cites W2070322626 @default.
- W2891749081 cites W2073812468 @default.
- W2891749081 cites W2099308462 @default.
- W2891749081 cites W2100879597 @default.
- W2891749081 cites W2129539511 @default.
- W2891749081 cites W2129644086 @default.
- W2891749081 cites W2130931342 @default.
- W2891749081 cites W2133665775 @default.
- W2891749081 cites W2142342155 @default.
- W2891749081 cites W2152404931 @default.
- W2891749081 cites W2162692770 @default.
- W2891749081 cites W2165398944 @default.
- W2891749081 cites W2182295979 @default.
- W2891749081 cites W2258211000 @default.
- W2891749081 cites W2280408335 @default.
- W2891749081 cites W2293889938 @default.
- W2891749081 cites W2310059960 @default.
- W2891749081 cites W2320663691 @default.
- W2891749081 cites W2466226663 @default.
- W2891749081 cites W2547411571 @default.
- W2891749081 cites W2590402370 @default.
- W2891749081 cites W2621347347 @default.
- W2891749081 cites W856265779 @default.
- W2891749081 doi "https://doi.org/10.1016/j.ins.2018.08.066" @default.
- W2891749081 hasPublicationYear "2019" @default.
- W2891749081 type Work @default.
- W2891749081 sameAs 2891749081 @default.
- W2891749081 citedByCount "29" @default.
- W2891749081 countsByYear W28917490812019 @default.
- W2891749081 countsByYear W28917490812020 @default.
- W2891749081 countsByYear W28917490812021 @default.
- W2891749081 countsByYear W28917490812022 @default.
- W2891749081 countsByYear W28917490812023 @default.
- W2891749081 crossrefType "journal-article" @default.
- W2891749081 hasAuthorship W2891749081A5013822484 @default.
- W2891749081 hasAuthorship W2891749081A5014654309 @default.
- W2891749081 hasAuthorship W2891749081A5059540876 @default.
- W2891749081 hasAuthorship W2891749081A5066144350 @default.
- W2891749081 hasAuthorship W2891749081A5068253534 @default.
- W2891749081 hasAuthorship W2891749081A5091485657 @default.
- W2891749081 hasBestOaLocation W28917490812 @default.
- W2891749081 hasConcept C106301342 @default.
- W2891749081 hasConcept C108583219 @default.
- W2891749081 hasConcept C121332964 @default.
- W2891749081 hasConcept C153180895 @default.
- W2891749081 hasConcept C154945302 @default.
- W2891749081 hasConcept C169760540 @default.
- W2891749081 hasConcept C26760741 @default.
- W2891749081 hasConcept C31972630 @default.
- W2891749081 hasConcept C41008148 @default.
- W2891749081 hasConcept C47432892 @default.
- W2891749081 hasConcept C52672216 @default.
- W2891749081 hasConcept C62520636 @default.
- W2891749081 hasConcept C65909025 @default.
- W2891749081 hasConcept C86803240 @default.
- W2891749081 hasConcept C97385483 @default.
- W2891749081 hasConceptScore W2891749081C106301342 @default.
- W2891749081 hasConceptScore W2891749081C108583219 @default.
- W2891749081 hasConceptScore W2891749081C121332964 @default.
- W2891749081 hasConceptScore W2891749081C153180895 @default.
- W2891749081 hasConceptScore W2891749081C154945302 @default.
- W2891749081 hasConceptScore W2891749081C169760540 @default.
- W2891749081 hasConceptScore W2891749081C26760741 @default.
- W2891749081 hasConceptScore W2891749081C31972630 @default.
- W2891749081 hasConceptScore W2891749081C41008148 @default.
- W2891749081 hasConceptScore W2891749081C47432892 @default.
- W2891749081 hasConceptScore W2891749081C52672216 @default.
- W2891749081 hasConceptScore W2891749081C62520636 @default.
- W2891749081 hasConceptScore W2891749081C65909025 @default.
- W2891749081 hasConceptScore W2891749081C86803240 @default.
- W2891749081 hasConceptScore W2891749081C97385483 @default.
- W2891749081 hasLocation W28917490811 @default.
- W2891749081 hasLocation W28917490812 @default.