No Reference Pansharpened Image Quality Assessment Through Deep Feature Similarity

Badal, Neeraj; Soundararajan, Rajiv; Garg, Ankur; Patil, Abhishek

doi:10.1109/jstars.2022.3199446

Cited by 7 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach effectively captures spatial-spectral features from different sources and results in more robust and representative metrics for evaluating FR performance. Badal et al [76] proposed a learning-based NR approach to assess the quality of pansharpened images. This approach can predict state-of-the-art reference-based measures such as Q2 n and SAM without requiring a reference image.…”

Section: B Methods Based On Learning Featuresmentioning

confidence: 99%

Assessing Full-Resolution Pansharpening Quality: A Comparative Study of Methods and Measurements

Guan

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Since the introduction of pansharpening, quality assessment has played a pivotal role in related remote sensing research to ensure the overall system's reliability. Full-resolution (FR) quality assessment is a debated research topic for applications. However, FR assessment faces challenges due to the absence of reference compared to reduced-resolution assessment. Moreover, the lack of ground truth makes measuring quality metrics even more challenging. To summarize the current measures for these two challenges, this article presents a comprehensive study of FR methods. We review various FR techniques and analyze how they extract spatial and spectral features from pansharpened images without reference to high-resolution multispectral images. A classification approach is proposed to group these methods based on their shared characteristics, making it easier for researchers and practitioners to compare and select the most appropriate FR method for specific applications. Furthermore, we provide a summary of strategies for measuring FR performance in the absence of ground truth. These strategies are classified into subjective and objective approaches. In addition, we conduct a board analysis on a large-scale public pansharpened database with unified measuring criteria. This unified analysis allows us to present experiments from a statistical perspective, measure FR protocols' performance, and provide a broad qualitative and quantitative analysis. Overall, this study contributes to the development of pansharpening and provides guidance for selecting appropriate FR methods, as well as strategies for measuring FR performance.

show abstract

Section: B Methods Based On Learning Featuresmentioning

confidence: 99%

Assessing Full-Resolution Pansharpening Quality: A Comparative Study of Methods and Measurements

Guan

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The prediction performances were evaluated based on the Spearman rank order correlation coefficient (SRCC), the Pearson correlation coefficient (PLCC), and the root-mean-square error (RMSE) between the predicted and ground truth image quality scores. We chose these evaluation measures as they are commonly used to evaluate image quality assessment of natural images [ 34 ].…”

Section: Methodsmentioning

confidence: 99%

“…In Equations (5)–(7) [ 34 ], N represents the number of images,

represents the predicted score of the IQA algorithm for the

image,

represents the label value for the

image, and

represents the difference between the rank of

and the rank of

.…”

Section: Methodsmentioning

confidence: 99%

No-Reference Quality Assessment of Extended Target Adaptive Optics Images Using Deep Neural Network

Gao,

Li,

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes a supervised deep neural network model for accomplishing highly efficient image quality assessment (IQA) for adaptive optics (AO) images. The AO imaging systems based on ground-based telescopes suffer from residual atmospheric turbulence, tracking error, and photoelectric noise, which can lead to varying degrees of image degradation, making image processing challenging. Currently, assessing the quality and selecting frames of AO images depend on either traditional IQA methods or manual evaluation by experienced researchers, neither of which is entirely reliable. The proposed network is trained by leveraging the similarity between the point spread function (PSF) of the degraded image and the Airy spot as its supervised training instead of relying on the features of the degraded image itself as a quality label. This approach is reflective of the relationship between the degradation factors of the AO imaging process and the image quality and does not require the analysis of the image’s specific feature or degradation model. The simulation test data show a Spearman’s rank correlation coefficient (SRCC) of 0.97, and our method was also validated using actual acquired AO images. The experimental results indicate that our method is more accurate in evaluating AO image quality compared to traditional IQA methods.

show abstract

“…Some researchers present NR-IQA methods based on statistical features for pan-sharpening images [39][40][41]. Deep features are used in some NR-IQA methods for pan-sharpening images [42,43]. An NR-IQA method based on deep features for remote sensing images was proposed in [44].…”

Section: No-reference Image Quality Assessmentmentioning

confidence: 99%

No-Reference Hyperspectral Image Quality Assessment via Ranking Feature Learning

Li,

Dong,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In hyperspectral image (HSI) reconstruction tasks, due to the lack of ground truth in real imaging processes, models are usually trained and validated on simulation datasets and then tested on real measurements captured by real HSI imaging systems. However, due to the gap between the simulation imaging process and the real imaging process, the best model validated on the simulation dataset may fail on real measurements. To obtain the best model for the real-world task, it is crucial to design a suitable no-reference HSI quality assessment metric to reflect the reconstruction performance of different models. In this paper, we propose a novel no-reference HSI quality assessment metric via ranking feature learning (R-NHSIQA), which calculates the Wasserstein distance between the distribution of the deep features of the reconstructed HSIs and the benchmark distribution. Additionally, by introducing the spectral self-attention mechanism, we propose a Spectral Transformer (S-Transformer) to extract the spatial-spectral representative deep features of HSIs. Furthermore, to extract quality-sensitive deep features, we use quality ranking as a pre-training task to enhance the representation capability of the S-Transformer. Finally, we introduce the Wasserstein distance to measure the distance between the distribution of the deep features and the benchmark distribution, improving the assessment capacity of our method, even with non-overlapping distributions. The experimental results demonstrate that the proposed metric yields consistent results with multiple full-reference image quality assessment (FR-IQA) metrics, validating the idea that the proposed metric can serve as a substitute for FR-IQA metrics in real-world tasks.

show abstract

No Reference Pansharpened Image Quality Assessment Through Deep Feature Similarity

Cited by 7 publications

References 41 publications

Assessing Full-Resolution Pansharpening Quality: A Comparative Study of Methods and Measurements

Assessing Full-Resolution Pansharpening Quality: A Comparative Study of Methods and Measurements

No-Reference Quality Assessment of Extended Target Adaptive Optics Images Using Deep Neural Network

No-Reference Hyperspectral Image Quality Assessment via Ranking Feature Learning

Contact Info

Product

Resources

About