×

Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics

News / News / Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics
21 October. 2019

Efficient Evaluation of Image Quality via
Deep-Learning Approximation of Perceptual
Metrics

Alessandro Artusi, Francesco Banterle, Fabio Carrara, and Alejandro Moreo

Congratulations to Dr. Alessandro Artusi, Team Leader of the DeepCamera Multidisciplinary Research Group, on his recently accepted publication with title "Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics".
 

Journal: IEEE Transaction on Image Processing Impact Factor 6.79

Digital Object Identifier: 10.1109/TIP.2019.2944079

 
Abstract:
Abstract—Image metrics based on Human Visual System (HVS) play a remarkable role in the evaluation of complex image processing algorithms. However, mimicking the HVS is known to be complex and computationally expensive (both in terms of time and memory), and its usage is thus limited to a few applications and to small input data. All of this makes such metrics not fully attractive in real-world scenarios. To address these issues, we propose Deep Image Quality Metric (DIQM), a deep-learning approach to learn the global image quality feature
(mean-opinion-score). DIQM can emulate existing visual metrics efficiently, reducing the computational costs by more than an order of magnitude with respect to existing implementations.
More News
EDUCOVTRACER - Education Of Immigrants In The Digital Covid-19...
CYENS Centre of excellence (formerly known as RISE) has completed the project EduCovTracer...
19 March. 2021
CALL FOR CHAPTERS FOR EDITED VOLUME
CALL FOR CHAPTERS FOR EDITED VOLUME Reinventing Presence: Museums and Emerging Technologies
10 March. 2021
CAIP 2021 - Call for papers
The 19th International Conference on Computer Analysis of Images and Patterns
01 February. 2021
A new name, a new home.
The Center began operations in 2018, with a small team of employees, and is reaching the end of...
29 December. 2020
Displaying results 1-4 (of 95)
 |<  < 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10  >  >|