Optimizing Multistage Discriminative Dictionaries for Blind Image Quality Assessment

Jiang, Qiuping; Shao, Feng; Wang, Lin; Gu, Ke; Jiang, Gangyi; Sun, Huifang

doi:10.1109/tmm.2017.2763321

Cited by 196 publications

(72 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the dependency on human opinion scores, the generic NR approaches can be roughly divided into two categories [ 13 ]: distance-based methods and learning-based methods. Distance-based methods express the image distortion as a simple distance between the model statistics of the pristine image and those of the distorted image [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Blind Image Quality Assessment of Natural Scenes Based on Entropy Differences in the DCT Domain

Yang

Zhang

et al. 2018

Entropy

View full text Add to dashboard Cite

Blind/no-reference image quality assessment is performed to accurately evaluate the perceptual quality of a distorted image without prior information from a reference image. In this paper, an effective blind image quality assessment approach based on entropy differences in the discrete cosine transform domain for natural images is proposed. Information entropy is an effective measure of the amount of information in an image. We find the discrete cosine transform coefficient distribution of distorted natural images shows a pulse-shape phenomenon, which directly affects the differences of entropy. Then, a Weibull model is used to fit the distributions of natural and distorted images. This is because the Weibull model sufficiently approximates the pulse-shape phenomenon as well as the sharp-peak and heavy-tail phenomena of natural scene statistics rules. Four features that are related to entropy differences and human visual system are extracted from the Weibull model for three scaling images. Image quality is assessed by the support vector regression method based on the extracted features. This blind Weibull statistics algorithm is thoroughly evaluated using three widely used databases: LIVE, TID2008, and CSIQ. The experimental results show that the performance of the proposed blind Weibull statistics method is highly consistent with that of human visual perception and greater than that of the state-of-the-art blind and full-reference image quality assessment methods in most cases.

show abstract

Section: Introductionmentioning

confidence: 99%

Blind Image Quality Assessment of Natural Scenes Based on Entropy Differences in the DCT Domain

Yang

Zhang

et al. 2018

Entropy

View full text Add to dashboard Cite

show abstract

“…From the perspective of neurophysiology [ 27 ], when visual neurons receive the external stimuli, the information carried by the stimulus can be correctly perceived, while sparse representation is exactly consistent with the perceptual process of the visual signal. Moreover, according to the previous studies about visual signal processing, it has been proven that sparse representation can effectively match the visual perception characteristics of mammalian organism and describe the image signals with their sparsity and redundancy [ 28 , 29 , 30 ]. Therefore, sparse representation is used to identify the specific distortion of TMI in this study, i.e., regional and global detail loss.…”

Section: The Proposed Rsra-btmi Methodsmentioning

confidence: 99%

Blind Tone-Mapped Image Quality Assessment Based on Regional Sparse Response and Aesthetics

Chen

et al. 2020

Entropy

View full text Add to dashboard Cite

High dynamic range (HDR) images give a strong disposition to capture all parts of natural scene information due to their wider brightness range than traditional low dynamic range (LDR) images. However, to visualize HDR images on common LDR displays, tone mapping operations (TMOs) are extra required, which inevitably lead to visual quality degradation, especially in the bright and dark regions. To evaluate the performance of different TMOs accurately, this paper proposes a blind tone-mapped image quality assessment method based on regional sparse response and aesthetics (RSRA-BTMI) by considering the influences of detail information and color on the human visual system. Specifically, for the detail loss in a tone-mapped image (TMI), multi-dictionaries are first designed for different brightness regions and whole TMI. Then regional sparse atoms aggregated by local entropy and global reconstruction residuals are presented to characterize the regional and global detail distortion in TMI, respectively. Besides, a few efficient aesthetic features are extracted to measure the color unnaturalness of TMI. Finally, all extracted features are linked with relevant subjective scores to conduct quality regression via random forest. Experimental results on the ESPL-LIVE HDR database demonstrate that the proposed RSRA-BTMI method is superior to the existing state-of-the-art blind TMI quality assessment methods.

show abstract

“…Considering that the last convolutional block of the DRN has set the dilation rate equal to 4, our dilated inception module can be viewed as an extended convolutional block of the DRN with a combination of three parallel dilated convolutions inside. In our experiments, we set [α, β, γ] = [4,8,16] which show a great improvement from the primary dilated or original inception module. The receptive fields of the outputs after our dilated inception module are diverse and relatively large which contribute to incorporate various contextual information at different scales.…”

Section: Proposed Dilated Inception Modulementioning

confidence: 99%

A Dilated Inception Network for Visual Saliency Prediction

Yang

Lin

Jiang

et al. 2020

IEEE Trans. Multimedia

Self Cite

128

View full text Add to dashboard Cite

Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible direction to approach the next improvement is to fully characterize the multiscale saliency-influential factors with a computationally-friendly module in DCNN architectures. In this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction. It captures multi-scale contextual features effectively with very limited extra parameters. Instead of utilizing parallel standard convolutions with different kernel sizes as the existing inception module, our proposed dilated inception module (DIM) uses parallel dilated convolutions with different dilation rates which can significantly reduce the computation load while enriching the diversity of receptive fields in feature maps. Moreover, the performance of our saliency model is further improved by using a set of linear normalization-based probability distribution distance metrics as loss functions. As such, we can formulate saliency prediction as a probability distribution prediction task for global saliency inference instead of a typical pixel-wise regression problem. Experimental results on several challenging saliency benchmark datasets demonstrate that our DINet with proposed loss functions can achieve state-of-the-art performance with shorter inference time.

show abstract

Optimizing Multistage Discriminative Dictionaries for Blind Image Quality Assessment

Cited by 196 publications

References 59 publications

Blind Image Quality Assessment of Natural Scenes Based on Entropy Differences in the DCT Domain

Blind Image Quality Assessment of Natural Scenes Based on Entropy Differences in the DCT Domain

Blind Tone-Mapped Image Quality Assessment Based on Regional Sparse Response and Aesthetics

A Dilated Inception Network for Visual Saliency Prediction

Contact Info

Product

Resources

About