-
公开(公告)号：US4783831A
公开(公告)日：1988-11-08
申请号：US777724
申请日：1985-09-19
CPC分类号： G06K9/4609 , G06K9/6255
摘要： This invention provides a method and apparatus for automatically producing a standard pattern for local pattern matching. According to the present invention, local patterns equivalent in size to a standard pattern to be obtained are successively removed from the image of an object being examined to prepare standard pattern candidates. Evaluation values representing appropriateness as a standard pattern are obtained from the local patterns successively removed or the local patterns together with the image of the object being examined. The evaluation values are used in an evaluation function expressing the uniqueness of the standard pattern and in an auxiliary evaluation function as an aid to the former. The standard pattern is selected using such evaluation values.
摘要翻译： 本发明提供一种用于自动产生用于局部模式匹配的标准模式的方法和装置。 根据本发明，从被检查对象的图像中连续地移除与要获得的标准图案相当的尺寸的局部图案以准备标准图案候选。 表示作为标准图案的适当性的评价值是从连续移除的局部图案或局部图案与被检查物体的图像一起获得的。 评价值用于表示标准图案的唯一性的评价函数和辅助评价函数中作为前者的辅助。 使用这样的评估值来选择标准图案。
-
公开(公告)号：US4334241A
公开(公告)日：1982-06-08
申请号：US140415
申请日：1980-04-14
CPC分类号： H01L21/67144 , H01L21/68 , H01L21/681
摘要： A pattern position detecting system includes an image pickup device to pick up the image of an object which includes a target pattern which is to be detected. On the basis of the output of the pickup device, local patterns of the image surface are successively cut out and positional coordinates of the local patterns are successively generated to indicate the typical positions of each of these local patterns. The respective local patterns are then compared with a standard pattern having the same feature as that of the target pattern and the degree of coincidence therebetween is detected. The different degrees of coincidence of the local patterns in the vicinity of a particular local pattern are then compared so as to successively sample the local pattern whose degrees of coincidence become a maximum, and the positional coordinates and degrees of coincidence of the respective local patterns whose degrees of coincidence become a maximum are then stored. The positional coordinates fulfilling the positional relationship inherent to the target pattern from among the positional coordinates finally selected are then sampled and the sampled positional coordinates are identified as indicating a position of the target pattern.
摘要翻译： 图案位置检测系统包括用于拾取包括要检测的目标图案的对象的图像的图像拾取装置。 基于拾取装置的输出，连续地切出图像表面的局部图案，并连续地生成局部图案的位置坐标，以指示这些局部图案中的每一个的典型位置。 然后将各个局部图案与具有与目标图案相同特征的标准图案进行比较，并且检测它们之间的一致程度。 然后比较特定局部图案附近的局部图案的不一致的一致度，以便连续取样其重合度变得最大的局部图案，以及各个局部图案的位置坐标和符合度 然后存储重合度变为最大值。 然后对从最终选择的位置坐标中到达目标图案的固有位置关系的位置坐标进行采样，将采样的位置坐标识别为指示目标图案的位置。
-
公开(公告)号：US4288816A
公开(公告)日：1981-09-08
申请号：US897133
申请日：1978-04-17
CPC分类号： G06T3/4007 , G06K9/36
摘要： A compressed image producing system is disclosed which comprises a buffer memory unit including a plurality of cascade-connected shift register stages to which image signals time-sequentially produced by the conversion of the respective picture elements of an image into the corresponding binary signals through the scanning of the image are successively applied, a partial image extracting unit including a plurality of registers which take in the image signals from the shift register stages respectively and parallely delivers the image signals bit by bit, and a sampling pulse generating circuit which generates sampling pulses at predetermined intervals. The respective shift registers of the buffer memory perform their data shift operations in response to the sampling pulses to intermittently take in the image signals so that sampling point data corresponding to the scanning lines in number are stored in each register and a plurality of compressed images constructed by different groups of the sampling points are continuously produced through the shifting of the image extracting position.
摘要翻译： 公开了一种压缩图像产生系统，其包括缓冲存储器单元，该缓冲存储器单元包括多个级联连接的移位寄存器级，通过扫描将图像的各个像素转换成相应的二进制信号而时间顺序产生的图像信号 连续施加图像的部分图像提取单元，包括多个寄存器的部分图像提取单元，其分别从移位寄存器阶段获取图像信号，并且逐个地并行传送图像信号;以及采样脉冲发生电路，其在 预定间隔。 缓冲存储器的相应移位寄存器响应采样脉冲执行其数据移位操作，间歇地取入图像信号，使与数字扫描线相对应的采样点数据存储在每个寄存器中，构成多个压缩图像 通过不同组的采样点通过图像提取位置的移位连续产生。
-
公开(公告)号：US4494139A
公开(公告)日：1985-01-15
申请号：US363456
申请日：1982-03-30
申请人： Yoshihiro Shima , Seiji Kashioka , Takeshi Uno , Kunio Suzuki
发明人： Yoshihiro Shima , Seiji Kashioka , Takeshi Uno , Kunio Suzuki
CPC分类号： H05K13/08
摘要： An automatic assembly system wherein parts supplied from a feeder are held by a holder and are automatically mounted onto predetermined positions of a circuit board; comprising a first image pickup device which images at least a portion of said circuit board, a second image pickup device which images at least a portion of the part held by the holder means, a signal processor which processes an output of said first image pickup device to detect a deviation of said circuit board from a reference position and which also processes an output of said second image pickup device to detect a magnitude of deviation between said part and the predetermined position of said circuit board, and a positioning device which operates under control of said signal processor so as to adjust said predetermined position of said circuit board to a position opposing to said part and also to move said part toward said circuit board.
摘要翻译： 一种自动组装系统，其中从供纸器供应的部件由保持器保持并自动安装到电路板的预定位置; 包括对所述电路板的至少一部分进行成像的第一图像拾取装置，对由保持装置保持的部分的至少一部分进行成像的第二图像拾取装置，处理所述第一图像拾取装置的输出的信号处理器 以检测所述电路板与参考位置的偏差，并且还处理所述第二图像拾取装置的输出以检测所述部分与所述电路板的预定位置之间的偏差的大小，以及在控制下操作的定位装置 以便将所述电路板的所述预定位置调整到与所述部分相对的位置，并且还使所述部分朝向所述电路板移动。
-
5.发明授权Method and device for inspecting the defect of a pattern represented on an article 失效用于检查在物品上表示的图案的缺陷的方法和装置
公开(公告)号：US4345312A
公开(公告)日：1982-08-17
申请号：US138990
申请日：1980-04-10
CPC分类号： G06K9/6203 , G07C3/14
摘要： Herein disclosed is a pattern defect inspecting method which is characterized: in that an image is picked up from an article having a preset pattern thereby to extract the data of the pattern to be inspected while shifting the article with respect to the standard position preset in a picking-up picture image; in that a parameter indicating the defective degree of the pattern to be inspected is determined on the basis of the aforementioned data extracted and the dictionary data stored in advance; in that the parameter indicating the minimum defective degree is extracted from among those determined for such plural patterns to be inspected as are extracted from the vicinity of the standard position; and in that the parameter extracted is compared with a preset threshold value thereby to determine the propriety of the pattern.
摘要翻译： 这里公开了一种图案缺陷检查方法，其特征在于，从具有预设图案的物品拾取图像，从而提取待检查图案的数据，同时相对于预设在 拍摄图像; 其特征在于，基于所提取的上述数据和预先存储的字典数据，确定表示所检查图案的不良度的参数; 其中从对标准位置附近提取的这些多个待检查图案确定的参数中提取表示最小缺陷度的参数; 并且将提取的参数与预设的阈值进行比较，从而确定图案的适当性。
-
6.发明授权公开(公告)号：US08571265B2
公开(公告)日：2013-10-29
申请号：US13547727
申请日：2012-07-12
IPC分类号： G06K9/00
CPC分类号： G01C21/3602 , G06T7/521 , G06T2207/10028 , G06T2207/20101 , G06T2207/20221 , G06T2207/30252
摘要： It is an object to measure a position of a feature around a road. An image memory unit stores images in which neighborhood of the road is captured. Further, a three-dimensional point cloud model memory unit 709 stores a point cloud showing three-dimensional coordinates obtained by laser measurement which is carried out simultaneously to the image-capturing of the images as a road surface shape model. Using an image point inputting unit 342, a pixel on a feature of a measurement target is specified by a user as a measurement image point. A neighborhood extracting unit 171 extracts a point which is located adjacent to the measurement image point and superimposed on the feature for the measurement target from the point cloud. A feature position calculating unit 174 outputs three-dimensional coordinates shown by the extracted point as three-dimensional coordinates of the feature for the measurement target.
摘要翻译： 测量道路周围的特征的位置是一个对象。 图像存储单元存储捕获道路邻域的图像。 此外，三维点云模型存储单元709将通过激光测量获得的三维坐标的点云存储在作为路面形状模型的图像拍摄同时进行。 使用图像点输入单元342，由用户指定测量对象的特征上的像素作为测量图像点。 邻域提取单元171从点云中提取与测量图像点相邻并且叠加在测量对象的特征上的点。 特征位置计算单元174输出由提取的点示出的三维坐标作为测量对象的特征的三维坐标。
-
公开(公告)号：US07106904B2
公开(公告)日：2006-09-12
申请号：US10041603
申请日：2002-01-10
申请人： Yoshihiro Shima
发明人： Yoshihiro Shima
CPC分类号： G06K9/00449
摘要： A form identification method which can identify forms without errors even if a form is inputted from a scanner in different direction or the form is enlarged/shrunk. A form registration method which enables change/modification of forms when form types are pre-registered. Inputted points as features are extracted from the form, modification of enlargement/shrinkage, rotation, or skew is made to the inputted points. Form types are identified based on minimum distances between the inputted point and pre-registered dictionary points. When registering a similar form type, warning can be displayed on the screen. In a system a dictionary registration station, a form identification station, and a form edit station are connected via a communication network. Each station operates in interlocking manner, identifies inputted forms, and registers them into a dictionary.
-
公开(公告)号：US06660949B2
公开(公告)日：2003-12-09
申请号：US09926074
申请日：2001-08-24
申请人： Yasushi Kamino , Takao Fukui , Yoshio Sekino , Kenji Miyauchi , Hideo Niinai , Tokunori Tanaka , Kazuya Okada , Ken Maeda , Yoshihiro Shima
发明人： Yasushi Kamino , Takao Fukui , Yoshio Sekino , Kenji Miyauchi , Hideo Niinai , Tokunori Tanaka , Kazuya Okada , Ken Maeda , Yoshihiro Shima
IPC分类号： H01H2700
CPC分类号： H01H27/002 , H01H2027/005
摘要： An actuator of the present invention comprises an operation key 2 to be inserted into a key insertion hole formed in the safety switch, and a base 3. The operation key 2 is held on the base 3 and capable of freely swinging in two orthogonal directions. The actuator also comprises means (e.g. a guide stopper 4 and engagement spaces 34) for selectively restricting the swinging movement of the operation key 2 to either of the two directions.
-
公开(公告)号：US5388167A
公开(公告)日：1995-02-07
申请号：US850303
申请日：1992-03-12
申请人： Masashi Koga , Hiroshi Sakou , Masaaki Fujinawa , Hiromichi Fujisawa , Tatsuya Murakami , Yoshihiro Shima , Tsugio Takahashi , Kazunori Kinoshita , Kiyomichi Kurino , Hidefumi Masuzaki
发明人： Masashi Koga , Hiroshi Sakou , Masaaki Fujinawa , Hiromichi Fujisawa , Tatsuya Murakami , Yoshihiro Shima , Tsugio Takahashi , Kazunori Kinoshita , Kiyomichi Kurino , Hidefumi Masuzaki
CPC分类号： H04N1/40093 , G06K9/2054 , G06K2209/01
摘要： A file document image input can have shading removed to produce a deshaded image that is useful for highly efficient compression encoding, to be thereafter stored and transmitted in such efficient encoded form. When the image is retrieved or received, the decoded and deshaded image may have shading returned to it by combining with a shaded template image stored in the template image memory or by synthesizing shading in specified regions. By removing shading from regions, optical character recognition, shading identification or other processing such as smear prevention can be enhanced.
摘要翻译： 文件文档图像输入可以去除阴影以产生对于高效压缩编码有用的去阴影图像，然后以这种有效的编码形式存储和传输。 当图像被检索或接收时，经解码和未映射的图像可以通过与存储在模板图像存储器中的阴影模板图像组合或者通过在指定区域中合成阴影而具有返回到其的阴影。 通过从区域去除阴影，可以提高光学字符识别，阴影识别或其它处理，如防污染。
-
公开(公告)号：US06246794B1
公开(公告)日：2001-06-12
申请号：US08763515
申请日：1996-12-11
申请人： Tatsuhiko Kagehiro , Masashi Koga , Hiroshi Sako , Hiromichi Fujisawa , Hisao Ogata , Yoshihiro Shima , Shigeru Watanabe , Masato Teramoto
发明人： Tatsuhiko Kagehiro , Masashi Koga , Hiroshi Sako , Hiromichi Fujisawa , Hisao Ogata , Yoshihiro Shima , Shigeru Watanabe , Masato Teramoto
IPC分类号： G06K918
CPC分类号： G06K9/80 , G06K9/344 , G06K9/72 , G06K2209/01
摘要： A character reading method has enhanced character segmentation accuracy and character string recognition accuracy for reading correctly hand-written addresses on postal matters. The method extracts provisional character patterns from image information of the address character string (step 206), creates a table 219 of tentative character patterns and implements the character classification for the tentative character patterns (step 207), extracts, specifically for characters of the street number portion of the address character string, periphery information (vertical and horizontal lengths, vertical/horizontal length ratio, pattern spacings, etc.) of tentative character patterns (step 212), and segments the character string into characters accurately based on the information (step 215).
摘要翻译： 字符读取方法具有增强的字符分割精度和字符串识别精度，可以正确地阅读手写地址在邮政事务上。 该方法从地址字符串的图像信息中提取临时字符模式（步骤206），创建临时字符模式的表219并实现临时字符模式的字符分类（步骤207），专门提取街道的字符 地址字符串的数字部分，临时字符图案的周边信息（垂直和水平长度，垂直/水平长度比，图案间隔等）（步骤212），并且基于该信息将字符串分割成字符 步骤215）。
-
-
-
-
-
-
-
-
-
搜索结果
18 条记录 (耗时 0.024 秒)
