The growing production of digital content and its dissemination across the worldwide web require eficient and precise management. In this context, image quality assessment measures (IQAMs) play a pivotal role in guiding the development of numerous image processing systems for compression, enhancement, and restoration. The structural similarity index (SSIM) is one of the most common IQAMs for estimating the similarity between a pristine reference image and its corrupted variant. The multi-scale SSIM is one of its most popular variants that allows assessing image quality at multiple spatial scales. This paper proposes a two-stage genetic programming (GP) approach to evolve novel multi-scale IQAMs, that are simultaneously more effective and efficient. We use GP to perform feature selection in the first stage, while the second stage generates the final solutions. The experimental results show that the proposed approach outperforms the existing MS-SSIM. A comprehensive analysis of the feature selection indicates that, for extracting multi-scale similarities, spatially-varying convolutions are more effective than dilated convolutions. Moreover, we provide evidence that the IQAMs learned for one database can be successfully transferred to previously unseen databases. We conclude the paper by presenting a set of evolved multi-scale IQAMs and providing their interpretation.

Bakurov, I., Buzzelli, M., Castelli, M., Schettini, R., Vanneschi, L. (2022). Genetic programming for structural similarity design at multiple spatial scales. In GECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference (pp.911-919) [10.1145/3512290.3528783].

Genetic programming for structural similarity design at multiple spatial scales

Buzzelli M.;Castelli M.;Schettini R.;Vanneschi L.
2022

Abstract

The growing production of digital content and its dissemination across the worldwide web require eficient and precise management. In this context, image quality assessment measures (IQAMs) play a pivotal role in guiding the development of numerous image processing systems for compression, enhancement, and restoration. The structural similarity index (SSIM) is one of the most common IQAMs for estimating the similarity between a pristine reference image and its corrupted variant. The multi-scale SSIM is one of its most popular variants that allows assessing image quality at multiple spatial scales. This paper proposes a two-stage genetic programming (GP) approach to evolve novel multi-scale IQAMs, that are simultaneously more effective and efficient. We use GP to perform feature selection in the first stage, while the second stage generates the final solutions. The experimental results show that the proposed approach outperforms the existing MS-SSIM. A comprehensive analysis of the feature selection indicates that, for extracting multi-scale similarities, spatially-varying convolutions are more effective than dilated convolutions. Moreover, we provide evidence that the IQAMs learned for one database can be successfully transferred to previously unseen databases. We conclude the paper by presenting a set of evolved multi-scale IQAMs and providing their interpretation.
Si
slide + paper
Scientifica
Dilated Convolutions; Evolutionary Computation; Genetic Programming; Image Processing; Image Quality Assessment; Multi-Scale Context; Multi-Scale Processing; Multi-Scale Structural Similarity Index; Spatially-Varying Kernels; Structural Similarity
English
2022 Genetic and Evolutionary Computation Conference, GECCO 2022 - 9 July 2022through 13 July 2022
9781450392372
Bakurov, I., Buzzelli, M., Castelli, M., Schettini, R., Vanneschi, L. (2022). Genetic programming for structural similarity design at multiple spatial scales. In GECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference (pp.911-919) [10.1145/3512290.3528783].
Bakurov, I; Buzzelli, M; Castelli, M; Schettini, R; Vanneschi, L
File in questo prodotto:
File Dimensione Formato  
Bakurov-2022-GECCO22-AAM.pdf

Solo gestori archivio

Descrizione: Proceedings
Tipologia di allegato: Author’s Accepted Manuscript, AAM (Post-print)
Dimensione 2.43 MB
Formato Adobe PDF
2.43 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: http://hdl.handle.net/10281/392150
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact