Blind quality index for camera images with natural scene statistics and patch-based sharpness assessment

Tang, Lijuan; Li, Leida; Gu, Ke; Sun, Xingming; Zhang, Jianying

doi:10.1016/j.jvcir.2016.07.007

Cited by 15 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method performs remarkably better than other methods in terms of all three measures, PLCC, SROCC and RMSE, as well as its non-robust counterpart (NRSN). Even compared with the latest method BQIC[23], our PLCC and SROCC are more than 9% and 8% better, respectively. This indicates a better correlation of our method with the human visual perception of the distorted images than other state-of-the-art NR-IQA methods.It is necessary to further analyse the effectiveness of each type of robust features and the different combinations of them.…”

mentioning

confidence: 81%

“…BRISQUE [14], BLIINDS-II [13], IDEAL [17], RISE [44], the method in [21], CIQM [45], BQIC [23,46] and the method in [22]. The experimental setting with leave-one-out cross validation [47] is commonly used in many NR-IQA method [18,21,35].…”

Section: Comparison On the Cid2013 Databasementioning

confidence: 99%

“…The method in [22] combines sharpness measure and compound noise estimation. The BQIC method [23] addresses this problem from two aspects, NSS and local sharpness. Despite these promising methods, there is still a lack of research on exploring robust statistics to improve the prediction accuracy and monotonicity of IQA (including NR-IQA) algorithms for photographic images .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

No-reference image quality assessment for photographic images based on robust statistics

et al. 2018

View full text Add to dashboard Cite

No-reference image quality assessment (NR-IQA) is developing rapidly, but there lacks of research on exploring robust statistics to improve the prediction accuracy and monotonicity of NR-IQA algorithms, in particular for assessing photographic images captured by different digital cameras where a variety of unknown distortions may happen. Hence this paper proposes a novel robuststatistics-based NR-IQA method (termed RSN) for photographic images. In RSN, we present three types of features based on robust statistics: robust natural scene statistics of multiple components, robust multi-order derivatives, and robust complementary features in the frequency domain. Then support vector regression is applied to predict image quality using the extracted features. Experimental results show that RSN remarkably outperforms state-of-the-art NR-IQA methods on the CID2013 database of photographic images, as well as on the popular LIVE and TID2013 databases.

show abstract

mentioning

confidence: 81%

Section: Comparison On the Cid2013 Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

No-reference image quality assessment for photographic images based on robust statistics

et al. 2018

View full text Add to dashboard Cite

show abstract

“…3) Sharpness detection based NR metric: sharpness detection has been widely used in 2D image quality assessment [93]- [95] and also in the side view based FR metric LOGS [52]. In this part, we will introduce its usage in NR metrics.…”

Section: Nr Metricsmentioning

confidence: 99%

Quality assessment of DIBR-synthesized views: An overview

et al. 2021

View full text Add to dashboard Cite

“…Techniques for image quality assessment (IQA) have been extensively studied in image and video applications [1]. For example, one of the selling points of modern mobile phones is their ability to capture and produce high-quality images [2]. The captured image is processed by using different techniques which usually have their own tuning parameters.…”

Section: Introductionmentioning

confidence: 99%