Color Design Decisions for Ceramic Products Based on Quantification of Perceptual Characteristics

Designing ceramic products involves balancing aesthetic appeal with user perception. While ceramic color is a key factor in user satisfaction, evaluating color perception is subjective and difficult to quantify. Prior research has shown that color perception varies among individuals, making it challenging to standardize design choices. This uncertainty limits the ability to create consistent, appealing ceramic products. No prior work had resolved how to map perceptual color semantics to measurable color parameters. That uncertainty drove the need for a more systematic approach. Existing methods rely on subjective feedback, which lacks precision. This gap motivated the development of a new method using machine learning to quantify perceptual color characteristics. The goal is to bridge the divide between user perception and objective color data. This paper introduces a novel approach to address these limitations.

The aim of this study is to develop a method for quantifying ceramic color characteristics using a Back Propagation (BP) neural network. The specific problem is the subjective and inconsistent nature of user evaluations of ceramic color. The motivation is to provide a reliable, data-driven approach for ceramic color design. Current methods lack precision in linking perceptual semantics to measurable color values. This study seeks to establish a predictive model for ceramic color perception. The approach combines perceptual data with neural network modeling. The study focuses on mapping perceptual features to color parameters. The goal is to improve the accuracy of color design decisions in ceramics. This method could enhance product design consistency and user satisfaction.

The study uses a Back Propagation (BP) neural network algorithm to quantify ceramic color characteristics. The semantic difference method and statistical analysis were employed to gather perceptual data from users. These data were combined with a neural network to explore the relationship between color features and user perception. The input layer of the model consists of quantified color semantic values. The output layer includes the L, A, and B color components. The model was trained to predict color parameters based on perceptual input. The trained model was used to generate color schemes for ceramic products. The effectiveness of the model was tested through case studies on daily-use ceramic products.

The BP neural network successfully mapped perceptual color semantics to measurable L, A, and B values. The model demonstrated a strong correlation between user perception and predicted color parameters. The case study on daily-use ceramic products confirmed the model's effectiveness. The method provided a reliable basis for color design decisions. The predicted color values matched user expectations with high accuracy. The model's training process showed convergence within acceptable error margins. The results suggest that the method can be applied to various ceramic products. The study verified the feasibility of using neural networks in ceramic color design.

The study concludes that the BP neural network model effectively links perceptual color semantics to measurable color parameters. The proposed method provides a reliable framework for ceramic color design. The case study confirmed the model's practical applicability. The findings suggest that the method can be used to improve design consistency. The model's accuracy supports its use in product development. The results align with the authors' claim that the method enhances design decisions. The study does not claim broader implications beyond ceramic color design. The authors emphasize the method's effectiveness in bridging subjective perception and objective data.