Interior Scene Coloring Design Model Combining Improved K-means and SAA

Abstract

Due to technological progress and changes in people’s aesthetic standards, traditional design models need to be constantly broken through, seeking more efficient and accurate design methods. Seeking effective design models to improve design efficiency and prediction accuracy is an important task. Therefore, this study proposes an indoor scene coloring design model that combines improved K-means clustering and simulated annealing algorithm for this important task. Based on the analysis of indoor scene coloring, particle swarm optimization algorithm is used to optimize K-means clustering to achieve color classification. Combined with simulated annealing algorithm, adaptive adjustment of lighting conditions is achieved to enhance the naturalness and realism of coloring. These results confirmed that the proposed method had the highest average F-value, with an average F-value of 92.524 and 143.601 on both datasets, respectively. The average ARI values were 0.361 and 0.897, respectively. The designed algorithm performed the best and converged faster than other three. Therefore, the proposed method can effectively ensure the consistency between the distribution of data objects after clustering and the actual situation. For indoor scene coloring design, it has important practical significance and provides new possible paths for  improving design efficiency and prediction accuracy.