Predicting Stereoscopic Image Quality via Stacked Auto-Encoders Based on Stereopsis Formation

Yang, Jiachen; Sim, Kyohoon; Lu, Wen; Jiang, Bin

doi:10.1109/tmm.2018.2889562

Cited by 39 publications

(16 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity of SSIM is very low, because it does not need to synthesize cyclopean map, and the accuracy is not as high as ours. It can be seen from Table 13, compared with reference [6], [37], [38], the complexity of our algorithm is the lowest, beacause our method extracts spatial domain features directly, which have lower computational complexity than the transform domain features. Moreover, we use our method to evaluate image quality without classifying the distortion type of images.…”

Section: G Computational Complexitymentioning

confidence: 90%

“…Moreover, we use our method to evaluate image quality without classifying the distortion type of images. The models in [37] and [38] use CNN and stack auto-encoders to predict image quality, although the overall performance of the models is competitive with ours, the complexity of this paper is lower than theirs. Compared with [15], the performance of our algorithm is better than it on LIVE Phase I and IVC Phase II and is competitive with it on other image databases, but the complexity is higher than it.…”

Section: G Computational Complexitymentioning

confidence: 92%

“…In order to verify the effectiveness of the SIQA model proposed in this paper, the proposed method is compared with some state-of-the-art SIQA methods, including FR-SIQA metrics (Lin et al [4], Khan and Channappayya [5], Chen et al [6], SSIM [42], Jiang et al [46]), RR-SIQA metrics (Ma et al [8]) and NR-SIQA metrics (SINQ [15], Yang et al [31], Zhou et al [32], Karimi et al [37], Yang et al [38], Fezza et al [41], BRISQUE [47]). In this paper, we utilize three commonly used criteria to quantify and verify the performance of the proposed method as well as all competing metrics.…”

Section: A Overall Performance Comparisonmentioning

confidence: 99%

“…The method of [37], Karimi et al extract features from synthesized phase and contrast maps and then use a stacked neural network model to learn the predict model of stereo images. In [38], the prediction performance of the model using stacked auto-encoders (SAE) to predict stereoscopic image quality is accurate, but the complexity is high.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Blind Stereo Image Quality Assessment Based on Binocular Visual Characteristics and Depth Perception

2020

View full text Add to dashboard Cite

The quality prediction of stereo images has great challenges without reference images. In this paper, we propose a novel no-reference stereo image quality assessment (NR-SIQA) model based on binocular visual characteristics and depth perception, which can effectively evaluate the quality of symmetric distortion and asymmetric distortion images. To be specific, we discriminate the different binocular behaviors by analyzing binocular visual characteristics, and construct the corresponding cyclopean view instead of single cyclopean view to simulate different binocular behaviors. Then, we extract monocular and binocular visual features from the left view, the right view and the synthetic cyclopean view. Furthermore, in order to evaluate the depth quality of the stereo image accurately, we extract the depth perception features from the weighted disparity map and the longitudinal correlation coefficient map. Finally, we construct the mapping relationship model from quality perception feature domain to quality score domain by training an adaptive enhancement algorithm based on support vector regression (SVR). We evaluate the performance of the proposed algorithm on four stereo image databases. The experimental results show that compared with the state-of-the-art full reference(FR), reduced reference(RR) and NR-SIQA algorithms, the proposed algorithm achieves highly competitive performance for both symmetric and asymmetric distortions. INDEX TERMS No reference, stereo image quality assessment, binocular visual characteristics, depth perception, longitudinal correlation coefficient map.

show abstract

Section: G Computational Complexitymentioning

confidence: 90%

Section: G Computational Complexitymentioning

confidence: 92%

Section: A Overall Performance Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Blind Stereo Image Quality Assessment Based on Binocular Visual Characteristics and Depth Perception

2020

View full text Add to dashboard Cite

show abstract

“…In fact, effective image feature selection is critical. Because this is an important prerequisite for accurate measurement of position and attitude measurements based on monocular vision, related image features and image operators can be further effectively utilized [17]. We hope to use this to highlight the differences in visual images under different information.…”

Section: Introductionmentioning

confidence: 99%

MFNN: Position and Attitude Measurement Neural Network Based on Multi-Feature Fusion

Man

Meng

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Accurate measurement of position and attitude information has become the basis of application engineering in related fields. Traditional position and attitude measurement schemes, including lasers, infrared light, etc., often place high demands on the measurement environment. The visual image-based measurement scheme needs to be combined with the actual situation to establish a complex pose calculation model. Therefore, exploring a measurement scheme for efficient solution has become an urgent need in related fields. In this paper, we propose a multi-feature fusion position and attitude measurement neural network (MFNN). We effectively introduce the HOG operator as an image feature and combine it with the original image for a specific ratio. At the same time, we draw on the utilization strategy of feature points in traditional measurement methods. By combining the extracted image feature points with the network, the measurement error of the six-dimensional information is effectively reduced. Based on this, we propose a new type of position and attitude measurement network architecture. MFNN has further improved the accuracy of related measurements. INDEX TERMS Position and attitude measurement, MFNN, multi-feature fusion, neural network.

show abstract

Review on Supervised and Unsupervised Learning Techniques for Electrical Power Systems: Algorithms and Applications

Chen¹

2021

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Machine learning (ML) has become a rising sophisticated technological application trend in the electrical industry in recent years. Such innovation provides optional methodologies for many existing applications, such as power and load profile forecasting, reliability evaluation, substation behavior detection and state observation of electrical equipment, and so on. This paper presents a review of various supervised and unsupervised ML techniques and applications for electrical power systems, including generation, transmission, distribution and micro-grid. The algorithms and applications are mainly summarized from IEEE journals and the interest of this paper shows the roles and developments of most used algorithms and its corresponding extensions and performance in different applications.

show abstract

Predicting Stereoscopic Image Quality via Stacked Auto-Encoders Based on Stereopsis Formation

Cited by 39 publications

References 54 publications

Blind Stereo Image Quality Assessment Based on Binocular Visual Characteristics and Depth Perception

Blind Stereo Image Quality Assessment Based on Binocular Visual Characteristics and Depth Perception

MFNN: Position and Attitude Measurement Neural Network Based on Multi-Feature Fusion

Review on Supervised and Unsupervised Learning Techniques for Electrical Power Systems: Algorithms and Applications

Contact Info

Product

Resources

About