An Artificial Intelligence Approach for Interpreting Creative Combinational Designs

TL;DR

This paper presents an AI-based method combining computer vision and NLP to interpret creative combinational designs by identifying their core components, achieving high accuracy and providing insights into limitations.

Contribution

It introduces a novel heuristic algorithm for computational interpretation of creative designs, integrating multiple AI architectures and comprehensive evaluation on a dedicated dataset.

Findings

Achieved 87.5% accuracy in identifying 'base' components.

Achieved 80% accuracy in identifying 'additive' components.

Provided analysis of error cases and bottleneck issues.

Abstract

Combinational creativity, a form of creativity involving the blending of familiar ideas, is pivotal in design innovation. While most research focuses on how combinational creativity in design is achieved through blending elements, this study focuses on the computational interpretation, specifically identifying the 'base' and 'additive' components that constitute a creative design. To achieve this goal, the authors propose a heuristic algorithm integrating computer vision and natural language processing technologies, and implement multiple approaches based on both discriminative and generative artificial intelligence architectures. A comprehensive evaluation was conducted on a dataset created for studying combinational creativity. Among the implementations of the proposed algorithm, the most effective approach demonstrated a high accuracy in interpretation, achieving 87.5% for identifying 'base' and 80% for 'additive'. We conduct a modular analysis and an ablation experiment to assess the performance of each part in our implementations. Additionally, the study includes an analysis of error cases and bottleneck issues, providing critical insights into the limitations and challenges inherent in the computational interpretation of creative designs.