Details

Autor(en) / Beteiligte

• Sun, Ruofan

Titel

Research on the Art Design of Green Clothing Based on Image Restoration Technology

Ist Teil von

• Proceedings of International Conference on Artificial Intelligence and Communication Technologies (ICAICT 2023), p.363-372

Ort / Verlag

Singapore: Springer Nature Singapore

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• How to ensure that clothing design has high-quality performance and artistic expression while using more green design concepts is an urgent problem for clothing design industry. In clothing art design, the lack of information collection and people’s visual differences easily lead to the loss of clothing image information. Therefore, it is necessary to repair and fill in the clothing image information to improve the image expression ability in clothing art design. For the information lost areas in clothing design, the image can be filled and repaired through the prior knowledge of the information intact areas to ensure the accuracy of information expression in clothing design. In this paper, the application of green design concept in clothing design is studied, and a clothing image feature restoration algorithm based on improved convolutional neural network (CNN) is proposed to explore the artistic expression of green design concept in clothing design. The simulation results show that, after many iterations, the recall rate of the improved CNN is obviously better than that of the traditional particle swarm optimization (PSO) algorithm, and the error is significantly reduced. Through the improvement of this paper, the convergence speed of CNN parameters is faster and the final model classification accuracy is higher. Therefore, under the concept of green design, it is feasible to use this algorithm to analyze the artistic expression of green design concept in clothing design.