Visual Similarity Assessment for Product Aesthetic Properties Using Single Reference Training
Year: 2025
Type: article
Abstract: Traditional product aesthetic evaluation requires extensive preference labeling for each design, limiting scalability and increasing costs. This study presents a novel single reference training approach that enables aesthetic preference assessment through visual similarity to a single highly preferred product. Using 30 home audio speakers, we collected aesthetic preference ratings from 44 participants on a 7-point Likert scale. Four deep learning approaches—Pre-trained CNN, Auto-encoder, Siamese Network, and Triplet Network—measured visual similarity between themost preferred reference products and remaining samples. Results demonstrated significant correlations between visual similarity and aesthetic preference: the Triplet Network achieved Pearson correlation coefficientr= 0.448 (p= 0.013), while Pre-trained CNN approach yieldedr= 0.478 (p= 0.008). After filtering high-variance products, correlations substantially improved tor= 0.738 (pr= 0.51 − 0.61), harmony (r= 0.36 − 0.37), dynamics (r= 0.55 − 0.65), and complexity (r= 0.42 − 0.56). Interaction models of multiple principal components increased explanatory power (R2= 0.4065), demonstrating that aesthetic preferences emerge from complex relationships among visual features. The findings prove that single reference training effectively extracts interpretable aesthetic properties from embedding spaces without explicit labeling. Our results suggest that highly preferred products contain multiple aesthetic preference-related properties, and deep learning models can successfully extract features corresponding to these properties. This approach provides an alternative aesthetic assessment from labor-intensive individual evaluation to efficient similarity-based inference, offering a methodology with reduced data requirements for product design evaluation and enabling evaluation of new designs.
Source: IEEE Access
Authors: Seok Young Hwang, Juseong Kim, Kicheol Pak
Institution: Hongik University
Language: English
Topic: Color perception and design
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W4412747803