A Deep Evaluator for Image Retargeting Quality by Geometrical and Contextual Interaction

@article{Jiang2020ADE,
  title={A Deep Evaluator for Image Retargeting Quality by Geometrical and Contextual Interaction},
  author={Bin Jiang and Jiachen Yang and Qinggang Meng and Baihua Li and Wen Lu},
  journal={IEEE Transactions on Cybernetics},
  year={2020},
  volume={50},
  pages={87-99}
}
An image is compressed or stretched during the multidevice displaying, which will have a very big impact on perception quality. In order to solve this problem, a variety of image retargeting methods have been proposed for the retargeting process. However, how to evaluate the results of different image retargeting is a very critical issue. In various application systems, the subjective evaluation method cannot be applied on a large scale. So we put this problem in the accurate objective-quality… 
View on IEEE
figshare.com
23 Citations
Background Citations
12
Methods Citations
1

23 Citations

Citation Type

Citation Type

Perceived depth quality - preserving visual comfort improvement method for stereoscopic 3D images
No-reference stereoscopic image quality evaluator with segmented monocular features and perceptual binocular features
Toward a Quality Predictor for Stereoscopic Images via Analysis of Human Binocular Visual Perception
TLDR
This paper proposes a full-reference objective quality evaluator for stereoscopic images by simulating binocular behaviors of the human visual system (HVS): Binocular interaction and depth perception.
Pairwise Learning to Rank for Image Quality Assessment
TLDR
An objective full-reference image quality assessment (FR-IQA) index based on pairwise learning to rank (PLR) achieves higher consistency with human subjective evaluation than the state-of-the-art IQA metrics.
No-Reference Quality Assessment of Stereoscopic Videos With Inter-Frame Cross on a Content-Rich Database
TLDR
A comprehensive subjective evaluation of stereoscopic video quality in newly established TJU-SVQA databases that contain various contents, mixed resolution coding and symmetrically/asymmetrically distorted stereoscopic videos and proposes a new inter-frame cross map to predict the objective quality scores.
Effective crowd counting using multi-resolution context and image quality assessment-guided training
A multiscale object detection approach for remote sensing images based on MSE-DenseNet and the dynamic anchor assignment
TLDR
This paper proposes a novel object detection approach based on the Multiscale-SELU-DenseNet (MSE- DenseNet) and the dynamic anchor assignment (DAA) strategy and shows that the proposed method outperforms state-of-the-art detection methods on the VHR-10 dataset and maintains a real-time detection speed.
Latitude and binocular perception based blind stereoscopic omnidirectional image quality assessment for VR system
ARC-Net: An Efficient Network for Building Extraction From High-Resolution Aerial Images
TLDR
Compared to available deep learning models, the proposed ARC-Net demonstrates better segmentation performance with less computational costs and is both effective and efficient in automatic building extraction from high-resolution aerial images.
ESFNet: Efficient Network for Building Extraction From High-Resolution Aerial Images
TLDR
A novel efficient network named ESFNet is proposed which employs separable factorized residual block and utilizes the dilated convolutions, aiming to preserve slight accuracy loss with low computational cost and memory consumption.
...
...

References

SHOWING 1-10 OF 59 REFERENCES
Learning Sparse Representation for Objective Image Retargeting Quality Assessment
TLDR
To create a compact and robust feature representation, two overcomplete dictionaries are learned to represent the distortion sensitive features of an image to explore the effectiveness of sparse representation for objective image retargeting quality assessment.
Objective Quality Assessment for Image Retargeting Based on Structural Similarity
TLDR
The experimental results show that IR-SSIM is better correlated with subjective evaluations than existing methods in the literature and embeds it into a multi-operator image retargeting process, which generates visually appealing retargeted results.
Image Retargeting Quality Assessment
TLDR
An objective metric simulating the human vision system (HVS) is presented, proposing to use a reverse order that organizes image features from global to local viewpoints, leading to a new objective assessment metric for retargeted images.
Objective Quality Assessment for Image Retargeting Based on Perceptual Geometric Distortion and Information Loss
TLDR
This paper proposes a novel full-reference objective metric for assessing visual quality of a retargeted image based on perceptual geometric distortion and information loss, and shows good consistency between the proposed objective metric and the subjective rankings.
Backward Registration-Based Aspect Ratio Similarity for Image Retargeting Quality Assessment
TLDR
Under the guidance of the geometric change, a novel aspect ratio similarity (ARS) metric is developed to evaluate the visual quality of retargeted images by exploiting the local block changes with a visual importance pooling strategy and Experimental results demonstrate that the proposed ARS can predict more accurate visualquality of retTargeted images compared with the state-of-the-art IRQA metrics.
Optimized Multioperator Image Retargeting Based on Perceptual Similarity Measure
TLDR
A new multioperator retargeted algorithm by using four retargeting operators of seam carving, cropping, warping, and scaling iteratively is proposed by using structural similarity (SSIM) to evaluate the similarity between the original andretargeted images.
Image retargeting quality assessment based on support vector regression
Image Retargeting Quality Assessment: A Study of Subjective Scores and Objective Metrics
TLDR
This paper builds an image retargeting quality database, and demonstrates that the metric performance can be further improved, by fusing the descriptors of shape distortion and content information loss.
Objective Quality Prediction of Image Retargeting Algorithms
TLDR
Experiments on the RetargetMe benchmark, as well as a comprehensive additional user study, demonstrate that the proposed objective quality assessment method outperforms other existing metrics, while correlating better with human judgements makes this metric a good predictor of subjective preference.
No-Reference Retargeted Image Quality Assessment Based on Pairwise Rank Learning
TLDR
Experimental results demonstrate that the proposed method can effectively depict the perceptual quality of the retargeted image, which can even perform comparably with the full-reference quality assessment methods.
...
...