基于卷积神经网络的石材镶嵌工艺颜色匹配方法

打开文本图片集

中图分类号：TP399；TU564.2 文献标志码：A 文章编号：1000-5013（2025）04-0393-07

Color Matching Method for Stone Tessellation Process Based on Convolutional Neural Network

XIE Biaofeng CHEN Shouhong HUANG Jixiang LI Jian xin HUANG Shengui

（1.Institute of Manufacturing Engineering，Huaqiao University，Xiamen 36lO21，China; 2.Nan'an-HQU Institute of Stone Industry Innovations Technology，Quanzhou 362342，China; 3.College of Mechanical Engineering and Automation，Huaqiao University，Xiamen 361o21，China）

Abstract：To addres the problem of time-consuming manual material selection and unstable product quality in the stone tesselation process，a color matching method based on convolutional neural network model is proposed. Stone samples scanned from the production workshop were preprocessed to construct the stone image dataset. Diferent convolutional neural networks were trained to screen out the best stone classification model. In order to validate the models effectiveness，the color region of the target image was extracted and used as the input for actual production. The results demonstrated that the products produced using the proposed method were excellent in terms of color consistency，and the visual perception effect was highly similar.The proposed method significantly improve the eficiency of stone selection and ensure the stability of product quality.

Keywords：tessellation process；stone classification；convolutional neural network；process optimization

石材镶嵌产品具有深厚的历史与文化积淀，活跃于许多公共艺术舞台及家庭装饰中[1-3]。（剩余7970字）