Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks

Yang, Hongtao; Shi, Peng; Zhong, Dixiu; Pan, Da; Ying, Zefeng

doi:10.1109/access.2019.2957235

Cited by 14 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And the superiority of the method was verified in TID2008 and TID2013 datasets. The same year, Yang et al (2019) designed a BIQA method with the advantages of self-generated samples and self-feedback training, called BIQA-GAN. GAN-based methods have the ability to learn local distortion characteristics and whole quality on the depth features of the image, and it can accomplish the mapping fitting of potential features to the target domain.…”

Section: Related Workmentioning

confidence: 99%

G2NPAN: GAN-guided nuance perceptual attention network for multimodal medical fusion image quality assessment

Tian,

Zhang

2024

Front. Neurosci.

View full text Add to dashboard Cite

Multimodal medical fusion images (MMFI) are formed by fusing medical images of two or more modalities with the aim of displaying as much valuable information as possible in a single image. However, due to the different strategies of various fusion algorithms, the quality of the generated fused images is uneven. Thus, an effective blind image quality assessment (BIQA) method is urgently required. The challenge of MMFI quality assessment is to enable the network to perceive the nuances between fused images of different qualities, and the key point for the success of BIQA is the availability of valid reference information. To this end, this work proposes a generative adversarial network (GAN) -guided nuance perceptual attention network (G2NPAN) to implement BIQA for MMFI. Specifically, we achieve the blind evaluation style via the design of a GAN and develop a Unique Feature Warehouse module to learn the effective features of fused images from the pixel level. The redesigned loss function guides the network to perceive the image quality. In the end, the class activation mapping supervised quality assessment network is employed to obtain the MMFI quality score. Extensive experiments and validation have been conducted in a database of medical fusion images, and the proposed method is superior to the state-of-the-art BIQA method.

show abstract

Section: Related Workmentioning

confidence: 99%

G2NPAN: GAN-guided nuance perceptual attention network for multimodal medical fusion image quality assessment

Tian,

Zhang

2024

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Table 1 shows the performance metrics of the proposed approach. For proper evaluation, the proposed method is compared with full reference (FR), reduced reference (RR), and no reference (NR) methods [29,30]. The deep learning-based no-reference method is also considered for performance comparison.…”

Section: Evalution Of Image Datasetsmentioning

confidence: 99%

An efficient image focus measure based on perceptual features analysis

Gaidhane

2024

Preprint

View full text Add to dashboard Cite

In this paper, a new approach no-reference image quality assessment (NR-IQA) focus measure based on the additivity of Renyi Entropy is proposed. In human and computer vision, image quality must be quantified with human perception. Therefore, perceptual features such as image texture and structure are analyzed. It allows us to achieve a better correlation with the subjective quality assessment. The probability coefficients of images are obtained to extract the human visual system (HVS) features, and significant image details are evaluated. The randomness in the information of the image is observed by considering the additivity of Renyi Entropy. The majority of objective IQA algorithms evaluate the image quality by comparing the original image with the distorted. The presented approach is tested on artificial images by introducing a certain amount of blur without noise and in the presence of noise. The effectuality and performance of the presented method on real-time images show consistent responses under blurred and noisy conditions. Moreover, the proposed method is evaluated with three publicly available data sets such as LIVE, TID2013, and CSIQ. The presented method is compared with various existing techniques in the literature, and it is evident from the experiments that the method has better monotonicity and improved focus measures. The proposed approach achieved better performance metrics such as SROCC, KRCC, and PLCC. The computation time and complexity of the presented approach are reduced due to the logarithmic function.

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

Blind Image Quality Assessment of Natural Distorted Image Based on Generative Adversarial Networks

Cited by 14 publications

References 52 publications

G2NPAN: GAN-guided nuance perceptual attention network for multimodal medical fusion image quality assessment

G2NPAN: GAN-guided nuance perceptual attention network for multimodal medical fusion image quality assessment

An efficient image focus measure based on perceptual features analysis

Quality Assessment on Authentically Distorted Images by Expanding Proxy Labels

Contact Info

Product

Resources

About