Full-reference image quality measures are a fundamental tool to approximate the human visual system in various applications for digital data management: from retrieval to compression to detection of unauthorized uses. Inspired by both the effectiveness and the simplicity of hand-crafted Structural Similarity Index Measure (SSIM), in this work, we present a framework for the formulation of SSIM-like image quality measures through genetic programming. We explore different terminal sets, defined from the building blocks of structural similarity at different levels of abstraction, and we propose a two-stage genetic optimization that exploits hoist mutation to constrain the complexity of the solutions. Our optimized measures are selected through a cross-dataset validation procedure, which results in superior performance against different versions of structural similarity, measured as correlation with human mean opinion scores. We also demonstrate how, by tuning on specific datasets, it is possible to obtain solutions that are competitive with (or even outperform) more complex image quality measures.

Bakurov, I., Buzzelli, M., Schettini, R., Castelli, M., Vanneschi, L. (2023). Full-Reference Image Quality Expression via Genetic Programming. IEEE TRANSACTIONS ON IMAGE PROCESSING, 32, 1458-1473 [10.1109/TIP.2023.3244662].

Full-Reference Image Quality Expression via Genetic Programming

Buzzelli, Marco
;
Schettini, Raimondo;Castelli, Mauro;Vanneschi, Leonardo
2023

Abstract

Full-reference image quality measures are a fundamental tool to approximate the human visual system in various applications for digital data management: from retrieval to compression to detection of unauthorized uses. Inspired by both the effectiveness and the simplicity of hand-crafted Structural Similarity Index Measure (SSIM), in this work, we present a framework for the formulation of SSIM-like image quality measures through genetic programming. We explore different terminal sets, defined from the building blocks of structural similarity at different levels of abstraction, and we propose a two-stage genetic optimization that exploits hoist mutation to constrain the complexity of the solutions. Our optimized measures are selected through a cross-dataset validation procedure, which results in superior performance against different versions of structural similarity, measured as correlation with human mean opinion scores. We also demonstrate how, by tuning on specific datasets, it is possible to obtain solutions that are competitive with (or even outperform) more complex image quality measures.
Articolo in rivista - Articolo scientifico
full-reference image quality assessment; genetic programming; Image quality; image similarity; SSIM;
English
17-feb-2023
2023
32
1458
1473
reserved
Bakurov, I., Buzzelli, M., Schettini, R., Castelli, M., Vanneschi, L. (2023). Full-Reference Image Quality Expression via Genetic Programming. IEEE TRANSACTIONS ON IMAGE PROCESSING, 32, 1458-1473 [10.1109/TIP.2023.3244662].
File in questo prodotto:
File Dimensione Formato  
Bakurov-2023-IEEE Trans Image Process-VoR.pdf

Solo gestori archivio

Descrizione: Article
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 3.17 MB
Formato Adobe PDF
3.17 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/404778
Citazioni
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 4
Social impact