Product image modelling optimisation design method based on improved support vector machine

Hua Song

International Journal of Product Development, 2024, vol. 28, issue 4, 227-240

Abstract: In order to make the image modelling of the product more in line with the design goals, this paper proposes an optimised design method for product image modelling based on improved support vector machines. Firstly, construct the ontology triplet of product image modelling and extract the lexical features of image modelling. Secondly, using chaos algorithm and particle swarm optimisation algorithm to improve support vector machine to more accurately capture product appearance features. Finally, based on the extraction results of product appearance features, simulated annealing algorithm was introduced as an optimisation tool to solve the optimisation design problem of product image modelling, achieving efficient optimisation of product image modelling. The experimental results show that for the four-door sedan, the target vocabulary scores of the image modelling method in this article all exceed 0.9, and the highest aesthetic score of the image modelling design reaches 96.67 points.

Keywords: improving support vector machines; product image modelling; optimise design; simulated annealing algorithm. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=143257 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijpdev:v:28:y:2024:i:4:p:227-240

Access Statistics for this article

More articles in International Journal of Product Development from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().