用于钢材缺陷的检测预警方法及系统

• Format: Patent
• Language: Chinese
• Published: 27.10.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

本发明提供了用于钢材缺陷的检测预警方法及系统，涉及图像处理技术领域，调用目标监测记录并逐工艺节点分割，确定节点监测图像集，搭建缺陷检测模型，基于节点监测图像集提取待检源数据，输入所述缺陷检测模型中，获取缺陷识别集，缺陷告警信息为附加输出信息，对缺陷识别集进行复修评估，生成缺陷评估列表，将缺陷评估列表作为缺陷检测结果，解决现有技术中存在的对于钢材缺陷的检测准确度与完备性不足，较之钢材实际状态存在偏差的技术问题，针对多个检测维度分别构建检测双通道，分割生产检测图像并逐节点进行处理通道匹配检测，保障检测严谨度，最大限度提高缺陷检测的准确度与完备性。 The invention provides a detection and early warning method and system for steel defects, and relates to the technical field of image processing, and the method comprises the steps: calling a target monitoring record, segmenting process nodes one by one, determining a node monitoring image set, building a defect detection model, extracting to-be-detected source data based on the node monitoring image set, inputting the to-be-detected source data into the defect detection model, and obtaining a defect recognition set; the defect alarm information is additional output information, performing rerepair evaluation on the defect identification set, generating a defect evaluation list, and taking the defect evaluation list as a defect detection r