数字化背景下基于深度学习的生成设计在视觉识别平台中的应用研究

Research on the Application of Generative Design based on Deep Learning in Visual Recognition Platform under Digital Background

在目前信息爆炸的时代,如何实现先进技术与艺术的高效联结,将视觉设计去中心化,得到了众多学者的广泛关注。研究以生成技术为设计流程的延展进行人机联合协作的方式,将卷积神经网络与生成对抗网络模型进行结合,同时引入条件的方式,在生成器结构的每层连接条件信息,利用谱归一化与组归一化相互配合的方式优化上述模型,最终构建条件深度卷积生成对抗网络模型(Conditional Depth Convolution to Generate Antagonism Network, CDCGAN)。研究结果表明,CDCGAN模型的平均准确率为97.28%,并且其在智能化视觉识别设计平台中的延展能力与学习能力非常优秀。综上所述,CDCGAN模型具有较好的性能与准确率,并能很好地应用于智能化视觉识别设计平台。

In the current era of information explosion,how to realize the efficient connection between advanced technology and art,and how to decentralize visual design,has been widely concerned by many scholars.Research a method of human-machine collaboration using generation technology as an extension of the design process,combining convolutional neural networks with generating adversarial network models,and introducing conditional methods to connect conditional information at each layer of the generator structure.Optimize the above model by using spectral normalization and group normalization in conjunction,Finally,a conditional depth convolution to generate an adversarial network model(CDCGAN)was constructed.The research results showed that the average accuracy of the CDCGAN model was 97.28%,and its extensibility and learning ability in the intelligent visual recognition design platform were excellent.In conclusion,CDCGAN model has good performance and accuracy,and can be well applied to intelligent visual recognition design platform.