• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control >Parametric modeling in food package defect imaging
【24h】

Parametric modeling in food package defect imaging

机译：食品包装缺陷成像中的参数化建模

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A novel approach in food package defect detection is proposednbased on system identification theory, in which the channel defectndetection problem can be regarded as the conventional systemnidentification problem, i.e., estimation of the system impulse responsenbased on the input-output sequence using parametric and nonparametricnmodels. The well-known parametric model ARX has been investigated innthis paper. The data are collected with a focused ultrasound transducern(17.3 MHz, 6.35-mm diameter, f/2, 173 Μm -6 dB pulse-echo lateralnbeam width at the focus) scanned over a rectangular grid, keeping thenpackages in the focus. Performance is measured in terms of detectionnrate, image contrast, and contrast-to-noise ratio. The results using thenARX model are compared with previous image formation techniques and alsoncompared with the non-parametric method, i.e., spectral analysis. Thenresults show that the ARX model has the comparable detection rate asnRFCS and higher detection rate than BAI and RFS (except 6-Μmnair-filled channel in plastic trilaminate film) for channel in plasticntrilaminate film. The ARX model has achieved the moderate contrastnenhancement and ranks second in contrast-to-noise ratio enhancementnamong the compared techniques. The ARX model has a low detection ratenfor channel defects in aluminum trilaminate film, which shows that itsnperformance is material-dependent. Finally, the parametric method, ARXnmodel demonstrates better performance than the non-parametric method,nspectral analysis for food package defect detection
机译：提出了一种基于系统识别理论的食品包装缺陷检测新方法，该方法可以将通道缺陷检测问题视为常规的系统识别问题，即基于输入输出序列的参数和非参数模型估计系统脉冲响应n。本文研究了著名的参数模型ARX。在聚焦的超声换能器（17.3 MHz，直径为6.35-mm，f / 2，173 Mm -6 dB聚焦处的脉冲回波横向束宽度）上通过矩形网格扫描收集数据，然后将包装保持在焦点上。性能是根据检测率，图像对比度和对比度噪声比来衡量的。使用thenARX模型的结果与先前的图像形成技术进行了比较，并且还与非参数方法（即光谱分析）进行了比较。结果表明，ARX模型在塑料三层层压薄膜中的通道具有可比的asnRFCS检测率，并且比BAI和RFS（除了塑料三层层压薄膜中的6 Mmnair填充通道）具有更高的检测率。 ARX模型已经实现了中等程度的对比度增强，并且在对比技术中的对比度与噪声比增强方面排名第二。 ARX模型对三叠层铝膜中通道缺陷的检测率低，这表明其性能与材料有关。最后，参数方法ARXnmodel表现出比非参数方法n光谱分析更好的性能，用于食品包装缺陷检测

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