Genetic programming for structural similarity design at multiple spatial scales

Illya Bakurov, Marco Buzzelli, Mauro Castelli, Raimondo Schettini, Leonardo Vanneschi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationGECCO ’22. Proceedings of the 2022 Genetic and Evolutionary Computation Conference
EditorsJonathan E. Fieldsend
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages911-919
Number of pages9
ISBN (Print)978-1-4503-9327-2
DOIs
Publication statusPublished - 1 Jul 2022
EventGECCO 2022 - The Genetic and Evolutionary Computation Conference - Boston, United States
Duration: 9 Jul 202213 Jul 2022
https://gecco-2022.sigevo.org/HomePage

Publication series

NameGECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference

Conference

ConferenceGECCO 2022 - The Genetic and Evolutionary Computation Conference
Abbreviated titleGECCO'22
Country/TerritoryUnited States
CityBoston
Period9/07/2213/07/22
Internet address

Keywords

  • Genetic Programming
  • Image Quality Assessment
  • Structural Similarity
  • Multi-Scale Structural Similarity Index
  • Dilated Convolutions
  • Spatially-Varying Kernels
  • Multi-Scale Context
  • Multi-Scale Processing
  • Evolutionary Computation
  • Image Processing

Fingerprint

Dive into the research topics of 'Genetic programming for structural similarity design at multiple spatial scales'. Together they form a unique fingerprint.

Cite this