Towards Automatic Image Enhancement with Genetic Programming and Machine Learning
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{correia:2022:AS,
-
author = "Joao Correia and Nereida Rodriguez-Fernandez and
Leonardo Vieira and Juan Romero and Penousal Machado",
-
title = "Towards Automatic Image Enhancement with Genetic
Programming and Machine Learning",
-
journal = "Applied Sciences",
-
year = "2022",
-
volume = "12",
-
number = "4",
-
keywords = "genetic algorithms, genetic programming",
-
ISSN = "2076-3417",
-
URL = "https://www.mdpi.com/2076-3417/12/4/2212",
-
DOI = "doi:10.3390/app12042212",
-
abstract = "Image Enhancement (IE) is an image processing
procedure in which the images original information is
improved, highlighting specific features to ease
post-processing analyses by a human or machine.
State-of-the-art image enhancement pipelines apply
solutions to fixed and static constraints to solve
specific issues in isolation. In this work, an IE
system for image marketing is proposed, more precisely,
real estate marketing, where the objective is to
enhance the commercial appeal of the images, while
maintaining a level of realism and similarity with the
original image. This work proposes a generic image
enhancement pipeline that combines state-of-the-art
image processing filters, Machine Learning methods, and
Evolutionary approaches, such as Genetic Programming
(GP), to create a dynamic framework for Image
Enhancement. The GP-based system is trained to optimise
4 metrics: Neural Image Assessment (NIMA) technical and
BRISQUE, which evaluate the technical quality of the
images; and NIMA aesthetics and PhotoILike, that
evaluate the commercial attractiveness. It is shown
that the GP model was able to find the best image
quality enhancement (0.97 NIMA Aesthetics), while
maintaining a high level of similarity with the
original images (Structural Similarity Index Measure
(SSIM) of 0.88). The framework has better performance
according to the image quality metrics than the
off-the-shelf image enhancement tool and the frameworks
isolated parts.",
-
notes = "also known as \cite{app12042212}",
- }
Genetic Programming entries for
Joao Nuno Goncalves Costa Cavaleiro Correia
Nereida Rodriguez-Fernandez
Leonardo Vieira
Juan Jesus Romero Cardalda
Penousal Machado
Citations