-
11.发明授权
公开(公告)号：EP1145186B1
公开(公告)日：2004-02-18
申请号：EP99963238.3
申请日：1999-11-13
申请人： DaimlerChrysler AG
IPC分类号： G06K9/72
CPC分类号： G06K9/00791 , B60K35/00 , G06K9/00818 , G06K9/685
摘要： The invention relates to a method and device that increase the power of previously known systems that recognize and display the contents of traffic signs. The invention reduces the amount of computer capacity required for real time operation and improves the display quality of the contents of known traffic signs. The system for recognizing and/or displaying traffic signs comprises a camera and an evaluation unit connected thereto for image recognition and/or display. Said system uses information stemming from at least one map-based navigation system and/or one travel information system in order to recognize and/or display the contents of traffic signs.
-
公开(公告)号：EP1145186A2
公开(公告)日：2001-10-17
申请号：EP99963238.3
申请日：1999-11-13
申请人： DaimlerChrysler AG
IPC分类号： G06K9/72
CPC分类号： G06K9/00791 , B60K35/00 , G06K9/00818 , G06K9/685
摘要： The invention relates to a method and device that increase the power of previously known systems that recognize and display the contents of traffic signs. The invention reduces the amount of computer capacity required for real time operation and improves the display quality of the contents of known traffic signs. The system for recognizing and/or displaying traffic signs comprises a camera and an evaluation unit connected thereto for image recognition and/or display. Said system uses information stemming from at least one map-based navigation system and/or one travel information system in order to recognize and/or display the contents of traffic signs.
-
公开(公告)号：EP1131803A1
公开(公告)日：2001-09-12
申请号：EP99963239.1
申请日：1999-11-13
申请人： DaimlerChrysler AG
IPC分类号： G08G1/0968 , G06K9/68
CPC分类号： G06K9/00791 , B60K35/00 , G06K9/00818 , G06K9/685
摘要： The invention relates to a method and a device enabling traffic signs to be recognized in a reliable, cost-effective manner requiring as little computing power as possible and allowing them to be displayed to an observer in the form of a memory aid. The reject rate with respect to the recognition of objects that are recognized as traffic signs remains low. According to the invention, image data from an image sensor is analyzed and classified in an information processing unit. Image sections and/or image data corresponding to a symbolic representation stored in a memory unit is/are archived in a memory unit and represented by means of a display unit on the basis of classification results. When the image data is further processed, the extracted objects are separated into specific classes and sub-classes of traffic-signs and classified. A synthetic image of a traffic sign is generated, stored in a memory unit and displayed by means of a display unit.
-
14.发明公开Adaptative method and apparatus for automatically classifying surface defects 审中-公开适应品Verfahren und Vorrichtung zur automatischen Klassifizierung vonOberflächendefekten
公开(公告)号：EP1061571A2
公开(公告)日：2000-12-20
申请号：EP00112704.2
申请日：2000-06-15
发明人： Ben-Porath, Ariel
IPC分类号： H01L21/66
CPC分类号： G06T7/001 , G06K9/6268 , G06K9/685 , G06T2207/20084 , G06T2207/30148 , H01L21/67271 , H01L21/67288
摘要： A method and apparatus is provided for automatically classifying a defect on the surface of a semiconductor wafer into one of a predetermined number of core classes using a core classifier employing boundary and topographical information. The defect is then further classified into a subclass of arbitrarily defined defects defined by the user with a specific adaptive classifier associated with the one core class and trained to classify defects only from a limited number of related core classes. Defects that cannot be classified by the core classifier or the specific adaptive classifiers are classified by a full classifier.
摘要翻译： 提供了一种使用使用边界和形貌信息的核心分类器将半导体晶片的表面上的缺陷自动分类为预定数量的核心类别之一的方法和装置。 然后，该缺陷被进一步分类为由用户定义的任意定义的缺陷的子类，其具有与一个核心类相关联的特定自适应分类器，并训练为仅从有限数量的相关核心类别分类缺陷。 不能由核心分类器或特定自适应分类器分类的缺陷由全分类器分类。
-
公开(公告)号：EP0582490A2
公开(公告)日：1994-02-09
申请号：EP93306265.5
申请日：1993-08-09
发明人： Bengtson, Michael
CPC分类号： G06K9/00463 , G06K9/685
摘要： A method of and apparatus for converting an original representation of a page element expressed in bitmap form into a page definition language representation of the page element develops an element approximation expressed in the page definition language, converts the element approximation into an approximation bitmap and compares the approximation bitmap to the original representation expressed in bitmap form to obtain an error indication. The error indication is checked to determine whether it meets a certain criterion and, if so, the element approximation is used as the page definition language representation. Otherwise, one or more further element approximations are developed until an element approximation is obtained that results in an error indication which meets the certain criterion.
-
公开(公告)号：EP0471473A2
公开(公告)日：1992-02-19
申请号：EP91307006.6
申请日：1991-07-31
发明人： Tanaka, Tetsuomi
IPC分类号： G06K9/56
CPC分类号： G06K9/6202 , G06K9/56 , G06K9/685 , G06K2209/01
摘要： This invention is to realize certain steps, required for recognition of input image information, by a hardware, thus enabling parallel processing and achieving a high-speed processing.
According to the present invention, the processes of recognition of the input image information, namely smoothing of the input image, detection of direction information in small blocks of the image information after smoothing, and counting of the direction information are executed by a hardware. Consequently the small blocks extracted in succession from the image information are processed in successive manner with the result submitted to the next step, so that a next block can be processed immediately after the processing of a block. It is therefore possible to prevent the drawback of the conventional software processing, in which the next step can only be started after all the image information has been processed, and to achieve a high-speed processing.摘要翻译： 本发明是通过硬件来实现对输入图像信息的识别所需的某些步骤，从而能够并行处理并实现高速处理。 根据本发明，通过硬件执行输入图像信息的识别处理，即输入图像的平滑处理，平滑后的图像信息的小块中的方向信息的检测和方向信息的计数。 因此，从图像信息中连续提取的小块被连续地处理，结果被提交到下一个步骤，使得可以在块的处理之后立即处理下一个块。 因此，可以防止常规软件处理的缺陷，其中仅在所有图像信息被处理之后才能开始下一步骤并且实现高速处理。
-
17.发明公开
公开(公告)号：EP0419259A2
公开(公告)日：1991-03-27
申请号：EP90310300.0
申请日：1990-09-20
申请人： NEC CORPORATION
IPC分类号： G06K9/68
CPC分类号： G06K9/685
摘要： On recognizing first through P-th input patterns as first through P-th recognized patterns (P being greater than one) by using a plurality of reference patterns and a plurality of memorized identifiers identifying the reference patterns, a processing circuit (35) processes the first through the P-th input patterns into first through Q-th provisional patterns different from one another, where Q is not greater than the above-mentioned plurality. A calculating circuit (50) calculates dissimilarity degrees had by the reference patterns relative to the first through the Q-th provisional patterns to select, with repetition allowed as selected patterns, the reference patterns which have the dissimilarity degrees less than a predetermined degree. The calculating circuit thereby selects R particular identifiers and S different identifiers from the memorized identifiers, where R plus S is not greater than P and is not less than the plurality. Each particular identifier and each different identifier identify only one pattern and one of at least two patterns of the selected patterns. The other at least one of the above-mentioned at least two patterns is identified by at least one of the R particular identifiers. A determining circuit (60) determines first through P-th output identifiers identifying the first through the P-th recognized patterns by using the R particular idenifiers as ones, R in number, and others, S in number, of the first through the P-th output identifiers.
摘要翻译： 在通过使用多个参考图案和识别参考图案的多个存储标识符来识别第一到第P输入图案作为第一至第P识别图案（P大于1）时，处理电路（35）处理 首先通过第P个输入模式变成彼此不同的第一至第Q临时图案，其中Q不大于上述多个。 计算电路（50）计算出相对于第一至第Q临时图案的参考图案所具有的不相似度，以选择具有相差度小于预定程度的参考图案作为所选择的图案。 因此，计算电路从存储的标识符中选择R个特定标识符和S个不同标识符，其中R plus S不大于P且不小于多个。 每个特定标识符和每个不同的标识符仅标识所选图案的一个图案和至少两个图案中的一个图案。 另外至少一个上述至少两个图案由R个特定标识符中的至少一个识别。 确定电路（60）通过使用R个特定标识符来确定第一至第P输出标识符，其中第一到第P输出标识符通过使用R个特定标识符，第一到第P个数目中的R， 第三个输出标识符。
-
公开(公告)号：EP0279655A3
公开(公告)日：1990-12-05
申请号：EP88301335.1
申请日：1988-02-17
申请人： SORICON CORPORATION
发明人： Wilber, Scott A. , Joffe, David , Duzee, Brian Van , Haas, Mark , Goldstein, Andrew , Wieland, Chris Mark , Fox, Thomas D.
CPC分类号： G06K9/42 , G06K9/3283 , G06K9/685 , G06K2209/01
摘要： An apparatus for character recognition comprising means (100, 130) for producing first signals corresponding to the image of a character to be identified, means (136) for standardizing said first signals to produce second signals therefrom, said standarizing means comprising means (111, 120; 133-135) for modifying said first signals to represent a physically modified character whereby said second signals represent said character modifified in a predetermined manner, means (122) for storing third signals corresponding to at least one characteristic of a plurality of different characters, and means (140) for comparing said second and third signals to identify said first mentioned character.
-
公开(公告)号：EP0204516A3
公开(公告)日：1990-01-31
申请号：EP86304088.7
申请日：1986-05-29
发明人： Roth, Scot D
IPC分类号： G06K9/48
CPC分类号： B25J9/1697 , G05B19/4182 , G06K9/48 , G06K9/685 , Y02P90/083
摘要： A practical vision system for controlling the positioning of a robot arm recognises and locates objects. The vision system (20, 30) processes binary images, but recognises objects based on boundary features such as lines, arcs, corners and holes instead of "blob features" such as area and best-fit ellipse. Consequently, the vision system can process two common situations not handled by blob analysis: merged blobs due to touching or overlapping parts and incomplete blobs due to low image contrast. The microprocessor-based system is interfaced to the robot system and can recognize up to five parts per second.
-
公开(公告)号：EP3384402A1
公开(公告)日：2018-10-10
申请号：EP15909919.1
申请日：2015-12-02
CPC分类号： G06F3/1257 , G06F3/1204 , G06F17/2211 , G06F17/2229 , G06F17/248 , G06K9/00463 , G06K9/685 , H04N1/233
摘要： In one example of the disclosure, a set of electronic document templates is accessed and instances of duplicated document content are identified. Display of a user notice for first duplicated document content is caused. Responsive to receipt of data indicative of a user instruction to create a component template for the first duplicated content, the component template is created and stored.
-
-
-
-
-
-
-
-
-
搜索结果
130 条记录 (耗时 0.017 秒)
