全参考图像质量评价回顾与展望
高敏娟， 党宏社， 魏立力， 刘国军， 张选德 - 电子学报, 2021 - ejournal.org.cn
全参考图像质量评价(Full Reference Image Quality Assessment, FR-IQA) 是IQA
领域广为研究的类型之一. 本文回顾了FR-IQA 的发展历程, 对FR-IQA 应用现状和通用FR-IQA …
领域广为研究的类型之一. 本文回顾了FR-IQA 的发展历程, 对FR-IQA 应用现状和通用FR-IQA …
Introspective learning: A two-stage approach for inference in neural networks
M Prabhushankar, G AlRegib - Advances in Neural …, 2022 - proceedings.neurips.cc
In this paper, we advocate for two stages in a neural network's decision making process. The
first is the existing feed-forward inference framework where patterns in given data are …
first is the existing feed-forward inference framework where patterns in given data are …
[HTML][HTML] Target acquisition performance in the presence of JPEG image compression
This paper presents an investigation on the effect of JPEG compression on the similarity
between the target image and the background, where the similarity is further used to …
between the target image and the background, where the similarity is further used to …
Full-reference image quality assessment based on an optimal linear combination of quality measures selected by simulated annealing
D Varga - Journal of Imaging, 2022 - mdpi.com
Digital images can be distorted or contaminated by noise in various steps of image
acquisition, transmission, and storage. Thus, the research of such algorithms, which can …
acquisition, transmission, and storage. Thus, the research of such algorithms, which can …
Saliency-guided local full-reference image quality assessment
D Varga - Signals, 2022 - mdpi.com
Research and development of image quality assessment (IQA) algorithms have been in the
focus of the computer vision and image processing community for decades. The intent of IQA …
focus of the computer vision and image processing community for decades. The intent of IQA …
Natural scene statistics model independent no-reference image quality assessment using patch based discrete cosine transform
Most of no-reference image quality assessment (NR-IQA) techniques reported in literature
have utilized transform coefficients, which are modeled using curve fitting to extract features …
have utilized transform coefficients, which are modeled using curve fitting to extract features …
Stochastic surprisal: An inferential measurement of free energy in neural networks
M Prabhushankar, G AlRegib - Frontiers in Neuroscience, 2023 - frontiersin.org
This paper conjectures and validates a framework that allows for action during inference in
supervised neural networks. Supervised neural networks are constructed with the objective …
supervised neural networks. Supervised neural networks are constructed with the objective …
Federated learning based nonlinear two-stage framework for full-reference image quality assessment: An application for biometric
The non-linearity in medical image processing is a critical issue. Because the privacy of the
medical image and loss of data is a major concern in recent years. Federated learning is a …
medical image and loss of data is a major concern in recent years. Federated learning is a …
QL-IQA: Learning distance distribution from quality levels for blind image quality assessment
R Gao, Z Huang, S Liu - Signal Processing: Image Communication, 2022 - Elsevier
Recently, blind image quality assessment (BIQA) has been intensively studied with deep
learning. However, the limited quality-annotated datasets restrict its further development …
learning. However, the limited quality-annotated datasets restrict its further development …
Distorted representation space characterization through backpropagated gradients
In this paper, we utilize weight gradients from backpropagation to characterize the
representation space learned by deep learning algorithms. We demonstrate the utility of …
representation space learned by deep learning algorithms. We demonstrate the utility of …