Please use this identifier to cite or link to this item:
Title: Towards Automatic Image Enhancement with Genetic Programming and Machine Learning
Authors: Correia, João 
Rodriguez-Fernandez, Nereida
Vieira, Leonardo 
Romero, Juan 
Machado, Penousal 
Keywords: genetic programming; image enhancement; image filters; computer vision
Issue Date: 2022
Project: Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia and the European Union (European Regional Development Fund-Galicia 2014- 2020 Program) grant ED431G 2019/01 
Ministry of Science and Innovation project Society Challenges (Ref. PID2020-118362RB-I00) 
Serial title, monograph or event: Applied Sciences (Switzerland)
Volume: 12
Issue: 4
Abstract: Image Enhancement (IE) is an image processing procedure in which the image’s 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 optimize 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 framework’s isolated parts.
ISSN: 2076-3417
DOI: 10.3390/app12042212
Rights: openAccess
Appears in Collections:I&D CISUC - Artigos em Revistas Internacionais

Show full item record

Page view(s)

checked on Sep 25, 2023


checked on Sep 25, 2023

Google ScholarTM




This item is licensed under a Creative Commons License Creative Commons