A Novel Patch Variance Biased Convolutional Neural Network for No-Reference Image Quality Assessment

Po, Lai-Man; Liu, Mengyang; Yuen, Wilson Y. F.; Li, Yuming; Xu, Xuyuan; Zhou, Chang; Wong, P.H.W.; Lau, Kin Wai; Luk, Hon-Tung

doi:10.1109/tcsvt.2019.2891159

Cited by 46 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We found that the performance of the proposed system is superior to that of other latest methods on the CSIQ, TID2013, and MDID IQA databases, except for DeepQA [13] for SROCC and PS-NRIQA [36] for LCC on the LIVE IQA database. On LIVE, LRDB yields the second highest performance for both LCC and SROCC.…”

Section: B Performance Comparisonmentioning

confidence: 77%

“…For FR-IQA, PSNR, SSIM and its successors (IW-SSIM [3] and DOG-SSIM [31]), handcrafted feature-based methods (VIF [5], VSI [32], MAD [24], GMSD [4], and FSIM(c) [11]) and recently proposed deep model-based IQA metrics (FR-DCNN [33], WaDIQaM [16], and DeepQA [13]) are included. The compared NR-IQA metrics contain DIQA [14], BLIINDS-II [34], DIIVINE [35], PS-NRIQA [36], and dipIQ [7].…”

Section: B Performance Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Long-Range Dependencies and High-Order Spatial Pooling for Deep Model-Based Full-Reference Image Quality Assessment

Liu

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Deep Learning based image quality assessment (IQA) has been shown to greatly improve the quality score prediction accuracy of images with single distortion. However, because these models lack generalizability and the accuracy of multidistortion-based image data is relatively low, designing reliable IQA systems is still an open issue. In this paper, we propose to introduce long-range dependencies between local artifacts and high-order spatial pooling into a convolutional neural network (CNN) model to improve the performance and generalizability of the full-reference IQA (FR-IQA). This long-range dependencies model is based on the hypothesis that local apparent artifacts can affect the overall image quality. The proposed network architecture adopts a non-local means algorithm to establish connections between all positions in the deep feature space and uses the Minkowski function to improve the non-linearity of the spatial pooling. Based on this architecture, a robust FR-IQA system has been constructed and evaluated on three well-known singledistortion-based IQA databases (LIVE, CSIQ, and TID2013) and a multidistortion-based IQA database (MDID). Experimental results demonstrate that, compared with the latest FR-IQA systems, the proposed long-range dependencies-boosted CNN-based FR-IQA system can achieve state-of-the-art performance. A comprehensive cross-database evaluation also shows that the proposed system is sufficiently generalized between different databases and multidistortion-based image data is more useful for training robust image quality metrics. INDEX TERMS Full-reference image quality assessment, quantization, long-range dependencies, convolutional neural networks, spatial pooling.

show abstract

Section: B Performance Comparisonmentioning

confidence: 77%

Section: B Performance Comparisonmentioning

confidence: 99%

Long-Range Dependencies and High-Order Spatial Pooling for Deep Model-Based Full-Reference Image Quality Assessment

Liu

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then, they fine-tuned the learned network using the squared Euclidean distance to regress the image quality scores. Po et al Po et al (2019) proposed to apply a variance-based weighting for the original regression image quality scores to avoid homogenous image patches for the network training and quality score estimation. Ahmad et.…”

Section: Introductionmentioning

confidence: 99%

Ultrasound volume projection image quality selection by ranking from convolutional RankNet

Liu

Ling

Banerjee

et al. 2021

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

“…As for image fidelity metrics approaches, structural similarity index matrix (SSIM) [ 13 ], feature-similarity index matrix (FSIM) [ 14 ], peak signal-to-Noise ratio (PSNR) [ 15 ], and mean square error (MSE) [ 16 ] are used to measure the similarity between an original image and a distorted image. Besides these conventional image fidelity metrics, several learnable IQA models have been proposed [ 17 , 18 , 19 , 20 ] to predict image quality. For instance, Yan et al [ 17 ] presented a multi-task CNN (Convolutional Neural Network) model to estimate the quality of an input image without any reference image.…”

Section: Introductionmentioning

confidence: 99%

DLNR-SIQA: Deep Learning-Based No-Reference Stitched Image Quality Assessment

Ullah

Irfan

Han

et al. 2020

Sensors

View full text Add to dashboard Cite

Due to recent advancements in virtual reality (VR) and augmented reality (AR), the demand for high quality immersive contents is a primary concern for production companies and consumers. Similarly, the topical record-breaking performance of deep learning in various domains of artificial intelligence has extended the attention of researchers to contribute to different fields of computer vision. To ensure the quality of immersive media contents using these advanced deep learning technologies, several learning based Stitched Image Quality Assessment methods have been proposed with reasonable performances. However, these methods are unable to localize, segment, and extract the stitching errors in panoramic images. Further, these methods used computationally complex procedures for quality assessment of panoramic images. With these motivations, in this paper, we propose a novel three-fold Deep Learning based No-Reference Stitched Image Quality Assessment (DLNR-SIQA) approach to evaluate the quality of immersive contents. In the first fold, we fined-tuned the state-of-the-art Mask R-CNN (Regional Convolutional Neural Network) on manually annotated various stitching error-based cropped images from the two publicly available datasets. In the second fold, we segment and localize various stitching errors present in the immersive contents. Finally, based on the distorted regions present in the immersive contents, we measured the overall quality of the stitched images. Unlike existing methods that only measure the quality of the images using deep features, our proposed method can efficiently segment and localize stitching errors and estimate the image quality by investigating segmented regions. We also carried out extensive qualitative and quantitative comparison with full reference image quality assessment (FR-IQA) and no reference image quality assessment (NR-IQA) on two publicly available datasets, where the proposed system outperformed the existing state-of-the-art techniques.

show abstract

A Novel Patch Variance Biased Convolutional Neural Network for No-Reference Image Quality Assessment

Cited by 46 publications

References 18 publications

Long-Range Dependencies and High-Order Spatial Pooling for Deep Model-Based Full-Reference Image Quality Assessment

Long-Range Dependencies and High-Order Spatial Pooling for Deep Model-Based Full-Reference Image Quality Assessment

Ultrasound volume projection image quality selection by ranking from convolutional RankNet

DLNR-SIQA: Deep Learning-Based No-Reference Stitched Image Quality Assessment

Contact Info

Product

Resources

About