Computer Vision Technology Integration and Art Education Practices for Modern Printmaking

Abstract

Printmaking has a long history and high artistic value, and it is challenging research to integrate computer vision technology into artists’ printmaking process. In this paper, the line, texture, and frequency features of modern prints are extracted according to their artistic characteristics and then restructured by a convolutional neural network. The parameters of the conversion network are updated using gradient descent, and CLIP is used as a pre-training model to establish a modern printmaking-style migration algorithm. Computer vision technology is used to construct a modern printmaking digital image simulation and synthesis system. Practice shows that the usability of the system is 67.675, which is close to the level of”good”in the process of creating modern printmaking art by art students. The system’s diverse features of real-time interaction, integration of digital resources, virtual scene construction and autonomous learning further enhance the cultivation of modern printmaking creative ability and have high practical significance in art education value.