公开(公告)号：US5459795A

公开(公告)日：1995-10-17

申请号：US219759

申请日：1994-03-29

申请人： Hideaki Kawamura ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Katsuhiro Kondoh ,  Iwao Ichikawa

发明人： Hideaki Kawamura ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Katsuhiro Kondoh ,  Iwao Ichikawa

IPC分类号： G01R31/309 ,  G06T7/00 ,  G06K9/00

CPC分类号： G06T7/0004 ,  G01R31/309 ,  G06T7/0006 ,  G06T2207/20044 ,  G06T2207/20144 ,  G06T2207/30141

摘要： A wiring pattern inspection apparatus for inspecting an abnormality of a wiring pattern formed on a printed circuit board, which is equipped with an optical image pickup device for optically illuminating a surface of the printed circuit board including the wiring pattern to photoelectrically convert optical information of the printed circuit board surface due to the optical illumination into a grey level image. This grey level image is converted into a bi-level image which separates the grey level image into the wiring pattern side and a background side of the wiring pattern. Thereafter, the bi-level image is once contracted by a first size and then expanded by a second size so as to eliminate a micro conductive portion left on the printed circuit board or a micro pinhole which can be disregarded in the abnormality inspection, thereby preventing the excessive detection.

摘要翻译： 一种用于检查形成在印刷电路板上的布线图案的异常的布线图形检查装置，其配备有用于光学照射包括布线图案的印刷电路板的表面的光学图像拾取装置，以光电转换 印刷电路板表面由于光学照明而成为灰度图像。 该灰度图像被转换成将灰度级图像分离成布线图案侧和布线图案的背景侧的双电平图像。 此后，双层图像一次收缩第一尺寸，然后扩大第二尺寸，以消除留在印刷电路板上的微导电部分或在异常检查中可忽略的微针孔，从而防止 过度检测。

公开(公告)号：US5787191A

公开(公告)日：1998-07-28

申请号：US467442

申请日：1995-06-06

申请人： Hideaki Kawamura ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Katsuhiro Kondoh ,  Iwao Ichikawa

发明人： Hideaki Kawamura ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Katsuhiro Kondoh ,  Iwao Ichikawa

IPC分类号： G01R31/309 ,  G06T7/00 ,  G06K9/36 ,  G06K9/00 ,  G06K9/40

CPC分类号： G06T7/0004 ,  G01R31/309 ,  G06T7/0006 ,  G06T2207/20044 ,  G06T2207/20144 ,  G06T2207/30141

摘要： A wiring pattern inspection apparatus for inspecting an abnormality of a wiring pattern formed on a printed circuit board, which is equipped with an optical image pickup device for optically illuminating a surface of the printed circuit board including the wiring pattern to photoelectrically convert optical information of the printed circuit board surface due to the optical illumination into a grey level image. This grey level image is converted into a bi-level image which separates the grey level image into the wiring pattern side and a background side of the wiring pattern. Thereafter, the bi-level image is once contracted by a first size and then expanded by a second size so as to eliminate a micro conductive portion left on the printed circuit board or a micro pinhole which can be disregarded in the abnormality inspection, thereby preventing the excessive detection.

公开(公告)号：US5608816A

公开(公告)日：1997-03-04

申请号：US305968

申请日：1994-09-15

申请人： Toyoki Kawahara ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Hideaki Kawamura

发明人： Toyoki Kawahara ,  Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Hideaki Kawamura

IPC分类号： G01N21/956 ,  G01R31/309 ,  G06T7/00 ,  G06K9/03 ,  H04N7/18

CPC分类号： G06T7/0006 ,  G01N21/956 ,  G01R31/309 ,  G06T2207/10024 ,  G06T2207/30141

摘要： Pieces of feature information in a bi-level image such as a width, a branching point and an ending point of a wiring pattern are detected in a design rule checking section according to a micro inspection to find out pieces of feature information departing from a design rule. Also, feature codes in the bi-level image such as a corner of the wiring pattern are detected in a specific shape detecting section according to a macro inspection. The feature information are compared with pieces of referential feature information pertaining to a non-defective wiring pattern in a first comparing and judging section to judge whether the wiring pattern indicated by the feature information is defective or non-defective. The feature codes are compared with referential feature codes pertaining to a non-defective wiring pattern in a second comparing and judging section to judge whether the wiring pattern indicated by the feature codes is defective or non-defective. Therefore, defective types and portions of the wiring pattern can be detected by performing the macro inspection and the micro inspection in parallel without dividing the wiring pattern into processed regions.

摘要翻译： 根据微观检查，在设计规则检查部中检测诸如布线图案的宽度，分支点和终点的双层图像中的特征信息的部分，以从设计中发现特征信息 规则。 此外，根据宏观检查，在特定形状检测部中检测诸如布线图案的角部的双电平图像中的特征码。 将特征信息与第一比较判断部中与无缺陷布线图案有关的参考特征信息进行比较，以判断由特征信息指示的布线图案是否有缺陷或无缺陷。 将特征代码与第二比较判断部分中与无缺陷布线图案有关的参考特征码进行比较，以判断由特征码指示的布线图案是否有缺陷或无缺陷。 因此，通过并行地进行宏观检查和微观检查，可以检测不良类型和布线图案的部分，而不将布线图案划分为加工区域。

公开(公告)号：US5214712A

公开(公告)日：1993-05-25

申请号：US757408

申请日：1991-09-10

申请人： Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Hideaki Kawamura ,  Masaaki Nakashima ,  Hidemi Takahashi

发明人： Atsuharu Yamamoto ,  Yuji Maruyama ,  Hidehiko Kawakami ,  Hideaki Kawamura ,  Masaaki Nakashima ,  Hidemi Takahashi

IPC分类号： G06T7/00

CPC分类号： G06T7/0004 ,  G06T7/0085 ,  G06T2207/20036 ,  G06T2207/30141

摘要： A pattern inspection system for inspecting a pattern of a land for a through-hole formed in a printed board. In the system there are included a first illumination device for optically illuminating the printed board, a second illumination device for illuminating the printed board with light modulated at a predetermined period and an image pickup responsive to reflection light and transmission light from the printed board due to the first and second illumination devices to photoelectrically convert the printed board into a gray level image. The gray level image is converted into a bi-level image by a bi-level conversion device and then converted into an edge image by an edge detecting device. The edge image is expanded and contracted by predetermined amounts so as to obtain a through-hole image corresponding to the through-hole. A defect detecting device detects a defect of the pattern of the printed board on the basis of the through-hole image and the bi-level image from the bi-level conversion device.

摘要翻译： 一种图案检查系统，用于检查形成在印刷电路板上的通孔的焊盘的图案。 在该系统中，包括用于光学照射印刷电路板的第一照明装置，用于以预定周期调制光的照明印刷电路板的第二照明装置和响应于来自印刷电路板的反射光和透射光的图像拾取器，由于 第一和第二照明装置将印刷电路板光电转换成灰度级图像。 灰度图像由双电平转换装置转换成双电平图像，然后由边缘检测装置转换成边缘图像。 边缘图像以预定量膨胀和收缩，以获得对应于通孔的通孔图像。 缺陷检测装置基于来自双电平转换装置的通孔图像和双电平图像来检测印刷电路板的图案的缺陷。

公开(公告)号：US5272763A

公开(公告)日：1993-12-21

申请号：US936324

申请日：1992-08-28

申请人： Yuji Maruyama ,  Atsuharu Yamamoto ,  Hidemi Takahashi ,  Hidehiko Kawakami

发明人： Yuji Maruyama ,  Atsuharu Yamamoto ,  Hidemi Takahashi ,  Hidehiko Kawakami

IPC分类号： G01R31/28 ,  G01R31/309 ,  G06T7/60 ,  G06K9/00

CPC分类号： G06K9/44 ,  G01R31/2805 ,  G01R31/309 ,  G06K9/00 ,  G06T7/60 ,  G06K2209/19

摘要： An inspection apparatus for inspecting a wiring pattern on a printed board by illuminating the printed board with light to photoelectrically convert light reflected from the printed board into an optical grey level image corresponding to the wiring pattern thereon, the grey level image being converted into a bi-level image. The inspection apparatus includes a thinning circuit to perform a thinning process for removing the bi-level image by one picture element from the background side of the wiring pattern, the thinning process being repeatedly performed predetermined times with respect to all of picture elements of the wiring pattern to output the number of repetitions of the thinning process and further to output a skeleton image. Also included is a distance image converter to output a distance conversion image where the number of repetitions is given as a distance value from the background of the wiring pattern. The inspection apparatus compares the distance value of the distance conversion image with one or more thresholds along the skeleton image. This arrangement allows direct detection of the wiring pattern width, thereby permitting the wiring pattern inspection with a simple structure.

摘要翻译： 一种检查装置，用于通过用光照射印刷板来检查印刷电路板上的布线图案，以将从印刷电路板反射的光光电转换成对应于其上的布线图案的光学灰度级图像，灰度图像被转换为​​双 级图像。 检查装置包括：稀疏电路，用于执行从布线图案的背景侧的一个图像元素去除双电平图像的稀疏处理，稀疏处理相对于布线的所有图像元素反复进行预定次数 模式以输出稀疏处理的重复次数并进一步输出骨架图像。 还包括距离图像转换器，用于输出距离转换图像，其中从布线图案的背景给出重复次数作为距离值。 检查装置将距离转换图像的距离值与骨架图像的一个以上阈值进行比较。 这种布置允许直接检测布线图案宽度，从而以简单的结构允许布线图案检查。

公开(公告)号：US06293466B1

公开(公告)日：2001-09-25

申请号：US09007146

申请日：1998-01-14

申请人： Mikio Fujita ,  Atsuharu Yamamoto ,  Toyoki Kawahara ,  Kunio Yoshida ,  Toru Asano ,  Shigeo Komizo

发明人： Mikio Fujita ,  Atsuharu Yamamoto ,  Toyoki Kawahara ,  Kunio Yoshida ,  Toru Asano ,  Shigeo Komizo

IPC分类号： G06K710

CPC分类号： G06K7/14

摘要： An image input section enters a document image including a bar code, and converts the document image into a binary image. A small pattern removing section removes small patterns from a binary image sent from the input section. A labeling section separates the binary image into labeled regions and calculates the feature quantity including a center position of each labeled region. A region detecting section makes a group of labeled regions spaced at a predetermined positional relationship based on their feature quantities and detects a bar code candidate region. A decoding section decodes the bar code based on the feature quantity involved in the bar code candidate region.

摘要翻译： 图像输入部分输入包括条形码的文档图像，并将文档图像转换为二进制图像。 小图案去除部分从输入部分发送的二进制图像中移除小图案。 标记部分将二进制图像分成标记区域，并计算包括每个标记区域的中心位置的特征量。 区域检测部分基于其特征量使一组标记区域以预定的位置关系间隔，并且检测条形码候选区域。 解码部分根据条形码候选区域中涉及的特征量对条形码进行解码。

公开(公告)号：US5134272A

公开(公告)日：1992-07-28

申请号：US379123

申请日：1989-07-13

申请人： Hiroyoshi Tsuchiya ,  Atsuharu Yamamoto ,  Kunio Sannomiya ,  Hiroaki Kotera ,  Katsuo Nakazato ,  Mikio Fujita ,  Shigeo Komizo

发明人： Hiroyoshi Tsuchiya ,  Atsuharu Yamamoto ,  Kunio Sannomiya ,  Hiroaki Kotera ,  Katsuo Nakazato ,  Mikio Fujita ,  Shigeo Komizo

IPC分类号： G06K7/10

CPC分类号： G06K7/10871 ,  G06K7/1093 ,  G06K7/1443 ,  G06K7/1456

摘要： An apparatus for receiving input data values representing an array of picture elements of a source image containing one or more bar code regions, whereby the input data values are converted to bi-level values representing black or white states which are stored in an image memory, while in addition the bi-level values are processed to obtain data representing an image in which a "skeleton" central portion of the bar code region appears as an all-black region, while background black regions are eliminated. A central position and the slope of a central axis of the bar code region are computed based on that "skeleton" region, and data values in the image memory which conform to the central axis are then read out, to read the bar code data.

公开(公告)号：US06367698B1

公开(公告)日：2002-04-09

申请号：US09527849

申请日：2000-03-17

申请人： Atsuharu Yamamoto ,  Mikio Fujita

发明人： Atsuharu Yamamoto ,  Mikio Fujita

IPC分类号： G06K710

CPC分类号： G06K7/10851 ,  G06K7/14 ,  G06K7/1452

摘要： A bar code reader which is suitable for decoding a four-state bar code such as a Postnet bar code and which is designed to extract a bar code correctly from a background in a captured image. The bar code reader includes a binary coding circuit transforming a captured image into a binary image, an image storage storing therein the binary image, a shrinking circuit shrinking each pattern in the binary image by k pixels, a vertical expansion circuit expanding each pattern in the image outputted from the shrinking circuit vertically by m pixel, an edge detector detecting a contour of each pattern in the image outputted from the vertical expansion circuit to produce an image containing an edge of each pattern, a horizontal expansion circuit expanding each pattern in the image outputted from the edge detector horizontally by n1 pixel, a horizontal contraction circuit contracting each pattern in the image outputted from the horizontal expansion circuit horizontally by n2, an identification circuit labeling patterns in the image outputted from the horizontal contraction circuit to identify the patterns, and a decoder. The identification circuit specifies a bar code area based on shape characteristics of the patterns. The decoder selects data on the image stored in the image storage which belongs in the bar code area specified by the identification circuit to decode the bar code.

摘要翻译： 一种适用于解码诸如Postnet条形码之类的四状态条形码的条码阅读器，其设计用于从拍摄图像的背景中正确提取条形码。 条形码读取器包括二进制编码电路，将拍摄图像变换为二进制图像，存储二进制图像的图像存储器，将二进制图像中的每个图案缩小为k个像素的缩小电路， 从收缩电路垂直输出的像素为m像素，边缘检测器检测从垂直扩展电路输出的图像中的每个图案的轮廓，以产生包含每个图案的边缘的图像;水平扩展电路，其扩展图像中的每个图案 从边缘检测器水平地输出n1像素的水平收缩电路，水平收缩电路将从水平扩展电路输出的图像中的每个图案水平地收缩n2，识别电路标记从水平收缩电路输出的图像中的图案以识别图案，以及 一个解码器 识别电路基于图案的形状特征来指定条形码区域。 解码器选择存储在由识别电路指定的条形码区域中的图像存储器中的图像上的数据，以解码条形码。

公开(公告)号：US06070800A

公开(公告)日：2000-06-06

申请号：US987110

申请日：1997-12-08

申请人： Mikio Fujita ,  Atsuharu Yamamoto ,  Toyoki Kawahara ,  Kuinio Yoshida ,  Toru Asano ,  Shigeo Komizo

发明人： Mikio Fujita ,  Atsuharu Yamamoto ,  Toyoki Kawahara ,  Kuinio Yoshida ,  Toru Asano ,  Shigeo Komizo

IPC分类号： G06K7/00 ,  G06K7/10 ,  G06K7/14 ,  G02B7/08 ,  G06K15/12

CPC分类号： G06K7/1443 ,  G06K7/14 ,  G06K7/1456

摘要： An image input section enters a document image including a bar code, and converts the document image into a binary image. An image memory section memorizes the binary image supplied from the image input section. A mask judging section performs a scanning operation using an M.times.M pixel window for detecting an alternate pattern from the binary image supplied from the image input section. A small pattern removing section removes small patterns from a binary image sent from the mask judging section. An expanding section expands a pattern involved in a binary image by an amount equivalent to k1 pixels when this binary image is sent from the small pattern removing section. A contracting section contracts a pattern involved in a binary image by an amount equivalent to k2 pixels when this binary image is sent from the expanding section. A region detecting section obtains the feature quantity of each pattern involved in a binary image sent from the contracting section, and detects a bar code candidate region based on the detected feature quantity. And, a decoding section decodes a detected bar code by reading a specific image region from the image memory section when the specific image region corresponds to the bar code candidate region detected by the region detecting section.

摘要翻译： 图像输入部分输入包括条形码的文档图像，并将文档图像转换为二进制图像。 图像存储部存储从图像输入部提供的二值图像。 掩模判定部分使用从图像输入部分提供的二进制图像中检测替代图案的MxM像素窗口进行扫描操作。 小图案去除部分从掩模判断部分发送的二进制图像中去除小图案。 当从小图案去除部分发送二进制图像时，扩展部分将涉及二进制图像的图案扩展相当于k1个像素的量。 当从扩展部分发送二进制图像时，收缩部分将涉及二进制图像的模式收合相当于k2个像素的量。 区域检测部分获得从收缩部分发送的二进制图像中涉及的每个模式的特征量，并且基于检测到的特征量检测条形码候选区域。 并且，当特定图像区域对应于由区域检测部分检测到的条形码候选区域时，解码部分通过从图像存储部分读取特定图像区域来解码检测到的条形码。