CNN-Based Cross-Dataset No-Reference Image Quality Assessment

Yang, Dan; Peltoketo, Veli-Tapani; Kämäräinen, Joni-Kristian

doi:10.1109/iccvw.2019.00485

Cited by 18 publications

(20 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those methods supposed natural images, and the machine learning was used to learn the statistics of natural images and the features of distortion. Recently the convolutional neural network (CNN) has been applied instead of the handcrafted features 23,24) . The use of a generative adversarial network has also been proposed 25) .…”

Section: Related Workmentioning

confidence: 99%

[Paper] Automatic Quality Evaluation of Whole Slide Images for the Practical Use of Whole Slide Imaging Scanner

Shakhawat

Nakamura

Kimura

et al. 2020

MTA

View full text Add to dashboard Cite

Previously, a referenceless quality evaluation method (RQM) was proposed by Hashimoto et al. to evaluate the quality of the scanned image 7) for the purpose of Abstract A whole slide imaging (WSI) scanner scans pathological-specimens to produce digital images for monitor-based diagnosis and analysis. However, the image quality is sometimes insufficient due to focus-error or noise, in which case the slide needs to be rescanned. In previous work, a referenceless quality evaluation technique was proposed, but some artifacts (i.e. tissue-fold, air-bubble) were detected as false positives. Those artifacts need to be ignored in determining whether rescanning is necessary or not, because they are not caused in the scanning but slide preparation stage. This paper proposes a method for a more practical system to assess WSI quality by distinguishing the origins of quality degradation; the focus-error or noise caused by the scanner and the artifact occurred in the slide preparation. In the method, a support vector machine detects artifacts first, and then quality is evaluated excluding artifact regions. The effectiveness of the proposed system has been experimentally demonstrated.

show abstract

Section: Related Workmentioning

confidence: 99%

[Paper] Automatic Quality Evaluation of Whole Slide Images for the Practical Use of Whole Slide Imaging Scanner

Shakhawat

Nakamura

Kimura

et al. 2020

MTA

View full text Add to dashboard Cite

show abstract

“…Module II models temporal-memory effect and it includes two sub-modules: a GRU network and a subjectively-inspired temporal pooling layer. Note that the GRU network is the unrolled version of one GRU and the parallel CNNs/FCs share weights consider pair-wise learning for mixed datasets training, while they use different loss functions for training (Yang et al 2019;Zhang et al 2019b;Krasula et al 2020). Yang et al (2019) use the margin ranking loss and the Euclidean loss.…”

Section: Mixed Datasets Trainingmentioning

confidence: 99%

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Jiang

2021

Int J Comput Vis

115

View full text Add to dashboard Cite

Video quality assessment (VQA) is an important problem in computer vision. The videos in computer vision applications are usually captured in the wild. We focus on automatically assessing the quality of in-the-wild videos, which is a challenging problem due to the absence of reference videos, the complexity of distortions, and the diversity of video contents. Moreover, the video contents and distortions among existing datasets are quite different, which leads to poor performance of datadriven methods in the cross-dataset evaluation setting. To improve the performance of quality assessment models, we borrow intuitions from human perception, specifically, content dependency and temporal-memory effects of human visual system. To face the cross-dataset evaluation challenge, we explore a mixed datasets training strategy for training a single VQA model with multiple datasets. The proposed unified framework explicitly includes three stages: relative quality assessor, nonlinear mapping, and dataset-specific perceptual scale alignment, to jointly predict relative quality, perceptual quality, and subjective quality. Experiments are conducted on four publicly available datasets for VQA in the wild, i.e., LIVE-VQC, LIVE-Qualcomm, KoNViD-1k, and CVD2014. The experimental results verify the effectiveness of the mixed datasets training strategy and prove the superior performance of the unified model in comparison with the state-of-the-art models. For reproducible research, we make the PyTorch implementation of our method available at https://github.com/lidq92/MDTVSFA. Keywords Content dependency • In-the-wild videos • Mixed datasets training • Temporal-memory effect • Video quality assessment Communicated by Mei Chen.

show abstract

“…In comparison, the performance of the EPL method based on the most proper amount of initial training data is compared with the most advanced NR-IQA methods, including: classical NR-IQA methods (BLIINDSS [30], BRISQUE [28], BWS [5], CORNIA [31], GMLOG [51], IL-NIQE [6], and FRIQUEE [34]), and DNN-based NR-IQA methods (CNN [12], RankIQA [23], BIECON [20], DIQaM [17], DIQA [22], CaHFI [52], NRVPD [53], ESD [54], VS-DDON [55], NQS-GAN [56], and ILGNet [57]). This method was also compared with the well-known DNN models, AlexNet [10], ResNet50 [48], and VGG-16 [26], which were modeled using the LIVEC database.…”

Section: Evaluation Processmentioning

confidence: 99%

“…When compared with using only hand-crafted features, the combined strategy outperforms. In addition, compared with the end-to-end deep learning methods (CNN [12], RankIQA [23], BIECON [20], DIQaM 17], DIQA [22], CaHFI [52], NRVPD [53], ESD [54], VS-DDON [55], NQS-GAN [56], and ILGNet [57]), since the above algorithms are mostly directed to synthetic distortion, the learning of the authentic distortion features is insufficient. Consequently, although it has not been adjusted by the IQA database, the proposed method is still superior to all the methods.…”

Section: Performance Comparisonmentioning

confidence: 99%

Quality Assessment on Authentically Distorted Images by Expanding Proxy Labels

Guan

2020

Electronics

View full text Add to dashboard Cite

In this paper, we propose a no-reference image quality assessment (NR-IQA) approach towards authentically distorted images, based on expanding proxy labels. In order to distinguish from the human labels, we define the quality score, which is generated by using a traditional NR-IQA algorithm, as “proxy labels”. “Proxy” means that the objective results are obtained by computer after the extraction and assessment of the image features, instead of human judging. To solve the problem of limited image quality assessment (IQA) dataset size, we adopt a cascading transfer-learning method. First, we obtain large numbers of proxy labels which denote the quality score of authentically distorted images by using a traditional no-reference IQA method. Then the deep network is trained by the proxy labels, in order to learn IQA-related knowledge from the amounts of images with their scores. Ultimately, we use fine-tuning to inherit knowledge represented in the trained network. During the procedure, the mapping relationship fits in with human visual perception closer. The experimental results demonstrate that the proposed algorithm shows an outstanding performance as compared with the existing algorithms. On the LIVE In the Wild Image Quality Challenge database and KonIQ-10k database (two standard databases for authentically distorted image quality assessment), the algorithm realized good consistency between human visual perception and the predicted quality score of authentically distorted images.

show abstract

CNN-Based Cross-Dataset No-Reference Image Quality Assessment

Cited by 18 publications

References 42 publications

[Paper] Automatic Quality Evaluation of Whole Slide Images for the Practical Use of Whole Slide Imaging Scanner

[Paper] Automatic Quality Evaluation of Whole Slide Images for the Practical Use of Whole Slide Imaging Scanner

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Quality Assessment on Authentically Distorted Images by Expanding Proxy Labels

Contact Info

Product

Resources

About