HyNet: A novel hybrid deep learning approach for efficient interior design texture retrieval
Junming Chen, Zichun Shao, Caichun Cen, Jiaqi Li
Abstract
Abstract Interior designers are suffering from a lack of intelligent design methods. This study aims to enhance the accuracy and efficiency of retrieval textures for interior design, which is a crucial step toward intelligent design. Currently, interior designers rely on repetitive tasks to obtain textures from websites, which is ineffective as a interior design often requires hundreds of textures. To address this issue, this study proposes a hybrid deep learning approach, HyNet, which boosts retrieval efficiency by recommending similar textures instead of blindly searching. Additionally, a new indoor texture dataset is created to support the application of artificial intelligence in this field. The results demonstrate that the proposed method’s ten recommended images achieve a high accuracy rate of 91.41%. This is a significant improvement in efficiency, which can facilitate the design industry’s progression towards intelligence. Overall, this study offers a promising solution to the challenges facing interior designers, and it has the potential to significantly enhance the industry’s productivity and innovation.