首页> 外文期刊>Revista rvore >Quantifica??o da falha na madeira em juntas coladas utilizando técnicas de vis?o artificial
【24h】

Quantifica??o da falha na madeira em juntas coladas utilizando técnicas de vis?o artificial

机译:使用人工视觉技术定量胶合接头中木材的故障

获取原文
           

摘要

It is possible to obtain several products by glueing wood. Internationally approved standards require wood adhesion to be tested according to standardized procedures, including in the results, shear stress and wood failure percentages. In order to estimate wood failure percentage, the ASTM D5266-99 standard suggests the use of a grid template printed on a transparent sheet. However, this evaluation is not only time-consuming but also subjective. This work developed and tested an algorithm to quantify the flawed wood areas by using a machine vision system, a faster and less subjective procedure. Two types of automatic threshold algorithms were tested. The glued wood samples were scanned after the shear tests under compression. It was concluded that automatic measurement can replace the manual grid method. The proposed algorithms presented an average absolute error of 3%, as compared to the manual grid method.
机译:可以通过胶木来获得几种产品。国际批准的标准要求根据标准化程序进行木材粘附,包括在结果,剪切应力和木制失效百分比中进行测试。为了估算木材失效百分比,ASTM D5266-99标准表明使用印刷在透明纸上的网格模板。然而,这种评估不仅耗时,而且是主观的。这项工作开发并测试了一种通过使用机器视觉系统来量化缺陷的木材区域的算法,这是一种更快和更少的主观程序。测试了两种类型的自动阈值算法。在压缩下剪切试验后扫描胶合木样品。它的结论是,自动测量可以取代手动网格法。与手动网格法相比,所提出的算法呈现3%的平均绝对误差。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号