The Design and Development of Traditional Elements in Visual Communication Design under the Perspective of New Media

This paper takes visual communication design as the entry point and reduces the complexity of the network model and the number of parameters by a convolutional neural network. The Faster R-CNN algorithm has been improved and is now used as the main algorithm for traditional element extraction and detection. The global detection and segmentation extraction algorithm based on U2-Net is utilized to reduce the depth of the network model, and the VGG16 algorithm is improved according to the characteristics of traditional elements, migration learning and its network structure in order to increase the sensory field and solve the problem of loss of accuracy of the feature maps on the basis of not changing the feature layer. An empirical study of traditional element extraction is conducted by using shadow costume patterns as an example. The results show that in multiple shadow images, the range of hues used for the five character types, namely, small Dan, Sheng, Jingsheng, Chou and old Dan, is H [0°, 210°] [345°, 360°], and medium-high saturation is dominant, and the range of brightness of the colors used is also basically the same, which is between 0.5-1. This research experiment verifies the feasibility of the element extraction algorithm, which can realize the feature extraction and classification of traditional elements, and its application in visual communication design can improve the visual impact of the works, provide consumers with more diversified design solutions, and can also effectively realize the innovative application and development of traditional elements. © 2023 Yifei Cai, published by Sciendo.