CMLsearch: Semantic visual search and simulation through segmented colour, material, and lighting in interior image

• DOI: 10.1093/jcde/qwae114
• Publication Date: 2024-12-31T02:29:07Z
• Authors: Semin Jin; Jiin Choi; Kyung Hoon Hyun
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Abstract In product search systems, user behavior changes according to their intentions, requiring adaptations in system requirements and information modeling. When purchasing home decor products, users must consider existing setting (EHS) the need pair multiple elements, not just a single product. However, no systems assist with varied intents (Target-Finding Decision-Making scenarios), nor have they focused on research that helps various elements of user's setting. Therefore, we introduce CMLsearch: semantic visual segments color, material, lighting, includes light CCT simulation. study (N = 44), CMLsearch significantly improved satisfaction decisions compared conventional systems. The reflected intent, offering object-level control supported more searches target-finding scenarios broader exploration decision-making scenarios. simulation further boosted confidence by allowing visualize products under different lighting conditions.