基于生成式深度学习方法的交互式徽标辅助设计系统研究

Research on Interactive Logo Aided Design System based on Generative Deep Learning Method

深度学习方法已应用于徽标设计领域,但现有的徽标设计工具缺少用户参与,无交互式编辑功能,在生成过程中缺少人机协同的考虑。因此,文章基于生成对抗网络模型,以及对于潜在空间的编辑控制,构建基于深度学习的交互式徽标设计系统LogoPaint,系统包含了输入、编辑、形状生成三个模块,并通过用户测试检验系统的性能。通过用户测试以及测试结果,证明该系统可以满足徽标设计的创作需求。基于深度学习技术的交互式徽标设计综合框架,能够有效辅助设计师完成徽标设计的构思过程,为深度学习技术在徽标设计领域的应用开创了新的思路。

The deep learning method has been applied to the logo design field,but the existing logo design tools lack user participation and interactive editing function,and lack the consideration of human-computer cooperation in the generation process.Based on the generative adversarial network and the editing control of potential space,LogoPaint based on deep learning is constructed.The system includes three modules:input,editing,and shape generation.The performance of the system is tested by user tests.Through user testing and test results,it is proved that the system can meet the creative needs of logo design.Conclusion the comprehensive framework of interactive logo design based on deep learning technology can effectively assist designers to complete the design process of logo design,and create new ideas for the application of deep learning technology in logo design.