基于机器视觉的铸坯表面缺陷检测系统的研制_技术交流_技术中心_中厚板 关键词：机器视觉；表面缺陷；图像处理；缺陷识别 [gap=1161]Keywords： machine vision；surface defect；image processing；Defect recognition
基于24个网页-相关网页
The glass defect recognition 玻璃缺陷识别
Apple defect recognition 苹果缺陷识别
fabric defect recognition 帘子布疵点识别
Intelligent Defect Recognition 缺陷智能识别
Defect recognition quality coefficient 缺陷识别质量系数
Defect signal recognition 缺陷信号识别
The defect recognition of strip is a complicate problem with multiple types and features, and using one classifying technology to achieve a one-step classifier with fine performance will be extremely difficult.
带钢表面缺陷识别是一个多类、多特征的复杂模式识别问题,采用单一分类器技术一步到位地构建具有优良性能的分类器十分困难。
参考来源 - 冷轧带钢表面缺陷机器视觉自动检测技术研究The traditional fault detection suffers from complicated process, low accurate ratio and off-line implement. The improved methods of defect recognition by artificial neural networks (ANN) can lead to the problems of overfit and bad generalization because of finite samples.
针对传统缺陷检测存在的检测手段落后、工序繁琐、准确率低、不易在线实施、受人为因素影响 ,以及用人工神经网络对小样本事件进行缺陷识别存在的过学习、推广性差等问题 ,从数据挖掘的角度 ,提出了直接从形成缺陷的影响因素着手 ,先消除工艺参数的冗余和噪声 ,再运用支持向量机分类算法 ,进行自动缺陷识别的新方法。
参考来源 - 基于支持向量机的缺陷识别方法·2,447,543篇论文数据，部分数据来源于NoteExpress
应用推荐