Art Suggester AI: The Art Recommendation Tool
Iain Macdonald, Harrison Johns, Angela Fernando, Ryan Brubacher, Johann Caancan, Aiden Henderson, Stefan Risca
CUCAI 2025 Proceedings • 2025
Abstract
Art Suggester is an AI-based art recommendation tool designed to inspire artists and enthusiasts by providing personalized art suggestions based on their available materials. The system uses a Convolutional Neural Network (CNN) to classify art mediums (e.g., paint, pencil crayons, markers) and a color detection algorithm to identify dominant colors in user-uploaded images. These inputs are used to recommend artworks from a curated database, making art discovery more accessible and engaging. Our CNN model achieved an accuracy of 95.12%, demonstrating its effectiveness in medium classification. The project highlights the potential of AI to bridge the gap between art creation and appreciation, offering a creative tool for artists and a learning resource for beginners. Code and resources are available at https://github.com/McMasterAI2024-2025/ArtSuggesterAI.