Blind image quality assessment with semantic information

Ji, Weiping; Wu, Jinjian; Shi, Guangming; Wan, Wenfei; Xie, Xiaodong

doi:10.1016/j.jvcir.2018.11.038

Cited by 18 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that human judgments of visual video quality are strongly influenced by the different sensitivity to low-level visual features [ 31 , 32 ] and the semantic video content [ 33 , 34 ], in this work we characterize video frames in terms of these two aspects. To this end, we employ two CNNs that we have called Extractor-Q and Extractor-S to extract low-level quality and semantic features, respectively.…”

Section: The Proposed Methodsmentioning

confidence: 99%

An Efficient Method for No-Reference Video Quality Assessment

2021

View full text Add to dashboard Cite

Methods for No-Reference Video Quality Assessment (NR-VQA) of consumer-produced video content are largely investigated due to the spread of databases containing videos affected by natural distortions. In this work, we design an effective and efficient method for NR-VQA. The proposed method exploits a novel sampling module capable of selecting a predetermined number of frames from the whole video sequence on which to base the quality assessment. It encodes both the quality attributes and semantic content of video frames using two lightweight Convolutional Neural Networks (CNNs). Then, it estimates the quality score of the entire video using a Support Vector Regressor (SVR). We compare the proposed method against several relevant state-of-the-art methods using four benchmark databases containing user generated videos (CVD2014, KoNViD-1k, LIVE-Qualcomm, and LIVE-VQC). The results show that the proposed method at a substantially lower computational cost predicts subjective video quality in line with the state of the art methods on individual databases and generalizes better than existing methods in cross-database setup.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

An Efficient Method for No-Reference Video Quality Assessment

2021

View full text Add to dashboard Cite

show abstract

“…Given that human judgments of visual video quality are strongly influenced by the different sensitivity to low-level visual psychological characteristics [ 27 , 34 ] and the semantic video content [ 25 , 26 ] in this work we characterize video frames in terms of these two aspects. To this end, we employ two CNNs that we have called Extractor-Q and Extractor-S to extract quality and semantic features, respectively.…”

Section: The Quality and Semantics Aware Video Quality Methodsmentioning

confidence: 99%

“…In this paper we focus on the problem of assessing the quality of videos affected by distortions introduced during the capture process. The proposed method relies on the rationale that human judgments of visual video quality depend on: the semantic content [ 25 , 26 ], the different sensitivity to low-level visual psychological characteristics [ 27 ], and the temporal-memory effects [ 11 ]. Image regions presenting clear semantic information are more sensitive to the presence of impairments, consequently they may be judged as more annoying by humans as they hinder the content recognition [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

No-Reference Quality Assessment of In-Capture Distorted Videos

2020

View full text Add to dashboard Cite

We introduce a no-reference method for the assessment of the quality of videos affected by in-capture distortions due to camera hardware and processing software. The proposed method encodes both quality attributes and semantic content of each video frame by using two Convolutional Neural Networks (CNNs) and then estimates the quality score of the whole video by using a Recurrent Neural Network (RNN), which models the temporal information. The extensive experiments conducted on four benchmark databases (CVD2014, KoNViD-1k, LIVE-Qualcomm, and LIVE-VQC) containing in-capture distortions demonstrate the effectiveness of the proposed method and its ability to generalize in cross-database setup.

show abstract

“…The network training on different metrics that were introduced for quality estimation. In [22], the authors have presented the quality of the images using structural semantics and spatial semantics. This was introduced to remove the quality of images by efficient noise removals.…”

Section: Literature Reviewmentioning

confidence: 99%

DCNN Based Technique to Analyze the Data of Foggy and Snowy Season

Harne

Choubey

2022

Preprint

View full text Add to dashboard Cite

Image Quality Analysis (IQA) is most significant concepts that is gaining attention among the researchers. Most images are considerably influenced by ambient lights. HumanVisual System perceives theimages quality in day and night time that causes the deprivation of luminance and features. In this article, we put forward an adaptive fuzzy-based DCNN technique that estimates the loss and enhancement of the images during seasonal changes. The natural scenery images are collected and preprocessed using Gaussian filter method that removes the unwanted noises. The preprocessed image is then guided with a guided filter method that helps to segment the seasonal changes of an image. The statistical features are extracted from the Adaptive Fuzzy-based Gamma Correction method that specifically leverages the gamma parameters using fuzzy-based decisional approach. Further on, the Deep Convolutional Neural Networks (DCNN) is running to classify the seasonal changes on images based on the computed image quality score. Investigational result have proven the accuracy of suggested technique in concerning of accuracy, precision and recall.

show abstract

Blind image quality assessment with semantic information

Cited by 18 publications

References 33 publications

An Efficient Method for No-Reference Video Quality Assessment

An Efficient Method for No-Reference Video Quality Assessment

No-Reference Quality Assessment of In-Capture Distorted Videos

DCNN Based Technique to Analyze the Data of Foggy and Snowy Season

Contact Info

Product

Resources

About