基于深度学习的纸病检测系统设计与研究

Design and Research of Deep Learning-based Paper Defect Detection System

关键词:  纸病检测  深度学习  系统设计  架构设计

Key Words:paper defect detection  deep learning  system design  architecture design

摘要:本课题设计了基于深度学习的纸病检测系统，用于提高造纸生产过程中的质量控制水平。该系统采用了“CCD+FPGA+工业控制计算机+训练计算机”的架构模式，实现了对纸张图像数据的实时采集、纸病的实时判断和纸病类型的实时识别。综合考虑分类准确率与推理速度，选择MobileNet模型算法，其分类准确率达99.5%，每秒可推理约103.1张分辨率为224×224的图像，满足现场纸病图像分类识别的实时要求。

Abstract:A deep learning-based paper defect detection system was designed in this paper to enhance the quality control of papermaking production. This system adopted the architecture model of “CCD + FPGA + industrial control computer + training computer”， achieving real-time collection of paper image data， real-time assessment of paper defects， and real-time identification of types of paper defects. Considering both classification accuracy and inference speed， the MobileNet model was chosen to achieve a classification accuracy of 99.5%. It could infer approximately 103.1 images per second with a resolution of 224×224， meeting the real-time requirements for on-site and recognition of pager defect image classification.