Intelligent Design and Personalized Optimization of Interior Colors Based on AI and Network Technology

Abstract

Traditional interior color design often ignores changes in environmental factors such as light changes and weather, resulting in a lack of adaptability in color performance, which affects the comfort and mood of residents. This paper applies an intelligent color dynamic adjustment method based on the Internet of Things (IoT) and deep learning, which can respond to environmental changes in real-time, optimize color design, and improve spatial comfort. First, the K-means clustering algorithm is used to divide the Lab color space into multiple color style areas, and the IoT sensors are deployed to collect environmental data in real-time in different areas. The MQTT (Message Queuing Telemetry Transport) protocol is used for data transmission, and the data is stored in a NoSQL database. The pre-trained ResNet model is used to extract features from interior images to obtain the visual features of the interior space. The extracted image features are fused with the environmental data collected by IoT to form an input dataset, and then the multi-layer perceptron is used to train the image features and environmental data to predict the color style of each area. The color style generated by GAN (Generative Adversarial Network) is iteratively optimized through user feedback. The system continuously adjusts the parameters of the generator and discriminator according to user preferences to make the final color scheme more in line with user needs. Experiments show that the EAI (Environment Adaptability Index) values under different lighting conditions range from 0.8 to 0.95, and the color difference ΔE reaches 0.1, which proves the potential application of this method in interior design.