Automated visual inspection apparatus
    2.
    发明授权
    Automated visual inspection apparatus 失效
    自动视觉检查仪

    公开(公告)号:US6031931A

    公开(公告)日:2000-02-29

    申请号:US615474

    申请日:1996-03-15

    IPC分类号: G06T7/00 G06K9/00 G06K9/48

    CPC分类号: G06T7/0085 G06T2207/30164

    摘要: Apparatus for determining at least one edge of an object having a plurality of openings with respective edges. An imaging device generates an image signal of the object to represent light intensity values of a plurality of pixels, the image signal being processed to estimate a linear relationship derived from the light intensity values of a predetermined number of the pixels. A determining device determines whether the linear relationship includes at least one light intensity value corresponding to an edge.

    摘要翻译: 用于确定具有相应边缘的多个开口的物体的至少一个边缘的装置。 成像装置生成对象的图像信号以表示多个像素的光强度值,该图像信号被处理以估计从预定数量的像素的光强度值导出的线性关系。 确定装置确定线性关系是否包括对应于边缘的至少一个光强度值。

    Adaptive lighting control apparatus for illuminating a variable-speed
web for inspection
    4.
    发明授权
    Adaptive lighting control apparatus for illuminating a variable-speed web for inspection 失效
    用于照明变速卷筒纸以进行检查的自适应照明控制装置

    公开(公告)号:US5870204A

    公开(公告)日:1999-02-09

    申请号:US907708

    申请日:1997-08-08

    IPC分类号: G01N21/89 G01N21/86

    CPC分类号: G01N21/8903

    摘要: A lighting control apparatus for illuminating a moving variable-speed web for inspection with a camera is provided. The apparatus is comprised of a detecting device for detecting the positioning of the web; a lighting device, aligned with the camera, for emitting a light to illuminate the web; a calculating device for calculating the speed of the web; and a control device which controls the emission of light by the lighting device as a function of the speed of the web.

    摘要翻译: 提供一种照明控制装置,用于照相用于检查的移动变速卷筒纸。 该装置由用于检测卷材的定位的检测装置组成; 与照相机对准的照明装置,用于发射光以照亮幅材; 用于计算网的速度的计算装置; 以及控制装置,其控制由照明装置发射的光作为幅材的速度的函数。

    Pattern searching method using neural networks and correlation
    5.
    发明授权
    Pattern searching method using neural networks and correlation 失效
    使用神经网络的模式搜索方法和相关性

    公开(公告)号:US5696838A

    公开(公告)日:1997-12-09

    申请号:US376544

    申请日:1995-01-23

    CPC分类号: G06K9/6203 G06K9/3233

    摘要: A pattern searching method using neural networks and correlation. This method combines the quickness and adaptiveness of neural networks with the accuracy of the mathematical correlation approach. Images are divided into small sub-images which are presented to the trained neural network. Sub-images that may contain the pattern or partial pattern are selected by the neural network. The neural network also provides the approximate location of the pattern, therefore the selected sub-images can be adjusted to contain the complete pattern. Desired patterns can be located by measuring the new sub-images' correlation values against the reference models in a small area. Experiments show that this superior method is able to find the desired patterns. Moreover, this method is much faster than traditional pattern searching methods which use only correlation.

    摘要翻译: 使用神经网络和相关性的模式搜索方法。 该方法将神经网络的快速性和适应性与数学相关方法的准确性相结合。 图像被分为呈现给训练神经网络的小的子图像。 可能包含图案或部分图案的子图像由神经网络选择。 神经网络还提供了图案的大致位置,因此可以调整所选择的子图像以包含完整图案。 可以通过在小区域中针对参考模型测量新的子图像的相关值来定位所需的图案。 实验表明,这种优越的方法能够找到所需的模式。 此外,该方法比仅使用相关性的传统模式搜索方法快得多。

    Pattern searching method using neural networks and correlation
    7.
    发明授权
    Pattern searching method using neural networks and correlation 失效
    使用神经网络的模式搜索方法和相关性

    公开(公告)号:US5995652A

    公开(公告)日:1999-11-30

    申请号:US910265

    申请日:1997-08-13

    IPC分类号: G06K9/32 G06K9/64 G06K9/62

    CPC分类号: G06K9/6203 G06K9/3233

    摘要: A pattern searching method using neural networks and correlation. This method combines the quickness and adaptiveness of neural networks with the accuracy of the mathematical correlation approach. Images are divided into small sub-images which are presented to the trained neural network. Sub-images that may contain the pattern or partial pattern are selected by the neural network. The neural network also provides the approximate location of the pattern, therefore the selected sub-images can be adjusted to contain the complete pattern. Desired patterns can be located by measuring the new sub-images' correlation values against the reference models in a small area. Experiments show that this superior method is able to find the desired patterns. Moreover, this method is much faster than traditional pattern searching methods which use only correlation.

    摘要翻译: 使用神经网络和相关性的模式搜索方法。 该方法将神经网络的快速性和适应性与数学相关方法的准确性相结合。 图像被分为呈现给训练神经网络的小的子图像。 可能包含图案或部分图案的子图像由神经网络选择。 神经网络还提供了图案的大致位置,因此可以调整所选择的子图像以包含完整图案。 可以通过在小区域中针对参考模型测量新的子图像的相关值来定位所需的图案。 实验表明,这种优越的方法能够找到所需的模式。 此外,该方法比仅使用相关性的传统模式搜索方法快得多。