-
">1.发明公开Verfahren und Anordnung zur Erfassung und/oder Erkennung komplexer Strukturen auf der Basis der "Fuzzy"-Theorie 失效方法和设备，用于检测和/或识别“模糊”理论的基础上复杂的结构。
公开(公告)号：EP0146824A1
公开(公告)日：1985-07-03
申请号：EP84114581.6
申请日：1984-11-30
CPC分类号： G06K9/74
摘要： Die aus den einzelnen Kenngrößen einer abzubildenden Struktur in einer Interferenzebene (IFE) gebildeten analogen Summenkenngrößen werden in geringer Anzahl unmittelbar als elektrische Signal verarbeitet, bewertet und digitalisiert der weiteren parallelen Verarbeitung zugeführt, so daß trotz der Anwendung des Holografieprinzips komplizierte optische Systeme und Filtersteuerungen vermieden werden. Filterungen zur Erkennung von bereits bekannten Strukturen können vielmehr rein digital durch Vergleich der erhaltenen Abbildungsinformationen mit den einzelnen Strukturen zugeordneten Bezugsinformationen (BZl..) digital vorgenommen werden.
Die Abbildung von Strukturen in der Interferenzebene (IFE) kann direkt mit kohärenter Strahlung durch holografische Abbildung oder aber indirekt durch Modulation von kohärenten Trägerwellen in getrennten Kanälen mit den Strukturkenngrößen erfolgen, wobei für die Interferenzbildung vorzugsweise ein optisches System, z.B. in Form eines Sternkopplers mit zwei an diesen angeschlossenen kohärenten Glasfaserbündeln, verwendet wird.摘要翻译： 1.和/或识别“模糊理论”的基础上复杂的结构，使用被描述所述respectivement给定结构中的特征值的并行信息处理，通过在干涉平面模拟总和特性值显示在检测的方法 ，从所有的特征值在一个较小的数，并且通过由单独的分析通道的同时出现的个体总和特性值的并行进一步处理，DASS它们在干涉平面（IFE）和所形成的总和特性值构成 被直接提供给模拟信号的形式的单独分析通道（AWK）各自评估作为电信号在雅舞蹈预定时间以均匀的计划，并直接或间接地转化要么成的副信息进行数字处理的项目，和 DASS模具的所有的分析通道的获取的数字子信息respectivement项（ AWK）一起同时提供给另外的数字信息处理阶段作为表征respectivement定结构中的数字图像信息。
-
-
公开(公告)号：EP2370938A2
公开(公告)日：2011-10-05
申请号：EP09796723.6
申请日：2009-12-21
申请人： THALES , Centre National de la Recherche Scientifique (C.N.R.S.) , Université Pierre et Marie Curie
摘要： Method for merging information of high semantic level representing complex situations composed of several objects originating from several sensors ci, said information possibly being heterogeneous, said method comprising the following steps: acquiring the various information emanating from said sensors in raw form and transforming it so as to convert it into the form of conceptual graphs, a conceptual graph representing several concepts and the relationships which exist between them, and being composed of entity nodes and of relationship nodes, with E the set of concept nodes defined on a support S, G
1 and G
2 two conceptual graphs defined on S, characterized in that the method determines a merging strategy denoted strategy
merge as follows: strategy
merge =f
merge Οf
comp :E xE→E∪{ E xE} where f
merge :{true, false} xE xE→E∪{ E xE} is a function for merging the concept nodes of the graphs, and f
comp : E xE→{true, false}xE xE is a function for testing compatibility between two concept nodes of the graphs, and in that the method comprises a step in the course of which said merging strategy is applied to the various information taking the form of the graphs.-
公开(公告)号：EP0615208A2
公开(公告)日：1994-09-14
申请号：EP94103633.7
申请日：1994-03-09
CPC分类号： G06K9/74
摘要： A self-organizing pattern learning system comprises an optical pattern correlation degree detecting means, which comprises a pattern storing means for storing a plurality of patterns, an input pattern displaying means for displaying a presented input pattern, and a photo detecting means. All or two of the input pattern displaying means, the pattern storing means, and the photo detecting means are located at positions adjacent to each other. The photo detecting means optically detects a degree of pattern correlation between the input pattern displayed on the input pattern displaying means and each of memory patterns stored in the pattern storing means. A learning pattern creating means creates a group of learning patterns in accordance with the degrees of pattern correlation, which have been detected by the optical pattern correlation degree detecting means, and the input pattern. A memory pattern updating means updates the memory patterns, which are stored in the pattern storing means, in accordance with the learning patterns, which have been created by the learning pattern creating means.
摘要翻译： 自组织图案学习系统包括光学图案相关度检测装置，其包括用于存储多个图案的图案存储装置，用于显示呈现的输入图案的输入图案显示装置和照片检测装置。 所有或两个输入图案显示装置，图案存储装置和光检测装置位于彼此相邻的位置。 光检测装置光学地检测在输入图案显示装置上显示的输入图案与存储在图案存储装置中的每个存储图案之间的图案相关程度。 学习模式创建装置根据由光学图案相关度检测装置检测到的图案相关度和输入图案，创建一组学习图案。 存储器模式更新装置根据由学习模式创建装置创建的学习模式来更新存储在模式存储装置中的存储器模式。
-
公开(公告)号：EP0474364A3
公开(公告)日：1993-09-29
申请号：EP91307207.0
申请日：1991-08-06
申请人： GEC-MARCONI LIMITED
CPC分类号： G06K9/82 , G06K9/6807
摘要： Apparatus for comparing an input genome sequence with one or more reference sequences comprises signal generators (10) for generating an input signal for each occurrence of each base component type (A,C,G,T) of the input sequence. A respective optical correlator (23-26) is provided for each base component type. Each correlator detects a match or near match between the occurrences of the respective base component type in the input sequence and the occurrences of that component type in any of the reference sequences, and produces a respective correlation signal. Decision-making circuitry (31) responds to the correlation signals from all of the correlators to provide an indication of a match or near match between the whole input sequence and any of the reference sequences.
摘要翻译： 用于将输入基因组序列与一个或多个参考序列进行比较的装置包括用于为输入序列的每个基本分量类型（A，C，G，T）的每次出现产生输入信号的信号发生器（10）。 为每个基本部件类型提供相应的光学相关器（23-26）。 每个相关器检测输入序列中相应基本分量类型的出现与任何参考序列中该分量类型的出现之间的匹配或近似匹配，并产生相应的相关信号。 决策电路（31）响应来自所有相关器的相关信号，以提供整个输入序列与任何参考序列之间的匹配或近似匹配的指示。
-
公开(公告)号：EP0032913B1
公开(公告)日：1986-04-23
申请号：EP80901365.9
申请日：1980-06-17
发明人： TODD, Robert , Haas, Frank Joseph
CPC分类号： G06K9/6807
摘要： A method and apparatus for dynamically switching between fonts or groups of fonts in an automatic character recognition system (10). The feature vector that the recognition system produces for each character on a document is normalized to unit length (24) and projected onto a set of eigenvectors (28). A memory (26) in the character recognition system stores several sets of eigenvectors, each set corresponding to a particular character font. A switch character which is included between a first and second group of characters triggers the selection of the appropriate set of eigenvectors for the succeeding font.
-
7.发明公开USER INTERFACE FOR USE IN SCREENING LUGGAGE, CONTAINERS, PARCELS OR PEOPLE AND APPARATUS FOR IMPLEMENTING SAME 审中-公开用户界面使用行李，容器，包装或个人及装置及其实施测试
公开(公告)号：EP1880331A4
公开(公告)日：2011-05-04
申请号：EP06741416
申请日：2006-04-25
申请人： OPTOSECURITY INC
发明人： BERGERON ERIC , LACHAPELLE JEAN , PERRON LUC , GENDRON MARC , COUTURE BERTRAND , BOUCHARD MICHEL R , LACASSE MARTIN
CPC分类号： G01V5/0008 , G06K9/741 , G06K2209/09
-
公开(公告)号：EP1700251A2
公开(公告)日：2006-09-13
申请号：EP04813253.4
申请日：2004-12-03
申请人： PITNEY BOWES INC.
IPC分类号： G06K15/02 , G06K9/20 , G06K9/82 , H04N1/04 , H04N1/23 , H04N1/50 , B41M3/14 , G01N21/33 , B42D15/00
CPC分类号： G06K9/2063 , G06K9/2018 , G06K2209/01
摘要： In accordance with an embodiment of the invention, a method for embedding key information into a printed document is disclosed. The method comprises creating a first section comprising a first ink having a first color under white light; and creating a second section comprising a second different ink. The second ink comprises a fluorescent ink and has a second color under white light which is substantially the same as the first color, and the fluorescent ink has a fluorescence when subjected to fluorescent-exciting radiation. The first section and the second section are visually indiscernible from each other on the printed document in white light. Also, the second section comprises key information, which is selected or highlighted by a user during creation of the document, and the first section comprises non-selected information.
-
公开(公告)号：EP0500315A3
公开(公告)日：1994-01-19
申请号：EP92301315.5
申请日：1992-02-18
摘要： 1. An optical method of recognition and classification of patterns or image, on real time basis, comprising
(a) measuring necessary times a respective output of correlation betwveen each of reference patterns and a specific pattern to be tested which is to belong to a specific class ; (b) calculating a representative value for each set of the correlation output, from the set of the measured data of the correlation outputs, in regard to said each of reference patterns and said specific pattern, and a respective parameter to represent the degree of the deviation of the measured data of said correlation outputs belonging to said each set of correlation outputs ; (c) making a respective membership function corresponding to each of said reference patterns for each of the specific classes to which the specific pattern should be classified or belong, on the basis of said respective representative value and said
respective parameter ;
(d) estimating a respective membership value to each of the respective membership function, assigned to each of the specific classes to which the pattern should be classified or belong, on the basis of the respective output of correlation between the pattern to be tested and said each of reference patterns ; (e) selecting the smallest membership value among the resulting membership values ; or estimating an average of all said resulting membership values ; (f) using the resulting smallest membership value or the resulting average as a degree to judge how much said pattern to be tested belongs to each of the specific classes.摘要翻译： 1.一种实时识别和分类图案或图像的光学方法，包括：（a）测量每个参考图案与待测试的特定图案之间的相关输出的相关输出的必要时间，所述特定图案属于特定 阶级 （b）针对所述每个参考图案和所述特定图案，从相关输出的测量数据的集合中计算每组相关输出的代表值，以及用于表示 属于所述每组相关输出的所述相关输出的测量数据的偏差; （c）基于所述相应代表值和所述相应参数，针对所述特定图案应被分类或属于的每个特定类别制作对应于每个所述参考图案的相应隶属函数; （d）基于要测试的模式与所述测试模式之间的相关输出的相应输出，估计分配给所述模式应被分类或属于的每个特定类别的相应隶属函数中的每一个的相应成员关系值 每个参考模式; （e）从所得到的成员资格值中选择最小的成员资格值; 或估计所有所述结果成员资格值的平均值; （f）使用得到的最小隶属度值或所得平均值作为程度来判断要测试的模式有多少属于每个特定类别。
-
公开(公告)号：EP0474364A2
公开(公告)日：1992-03-11
申请号：EP91307207.0
申请日：1991-08-06
申请人： GEC-MARCONI LIMITED
CPC分类号： G06K9/82 , G06K9/6807
摘要： Apparatus for comparing an input genome sequence with one or more reference sequences comprises signal generators (10) for generating an input signal for each occurrence of each base component type (A,C,G,T) of the input sequence. A respective optical correlator (23-26) is provided for each base component type. Each correlator detects a match or near match between the occurrences of the respective base component type in the input sequence and the occurrences of that component type in any of the reference sequences, and produces a respective correlation signal. Decision-making circuitry (31) responds to the correlation signals from all of the correlators to provide an indication of a match or near match between the whole input sequence and any of the reference sequences.
摘要翻译： 用于将输入基因组序列与一个或多个参考序列进行比较的装置包括用于为输入序列的每个基本分量类型（A，C，G，T）的每次出现产生输入信号的信号发生器（10）。 为每个基本部件类型提供相应的光学相关器（23-26）。 每个相关器检测输入序列中相应基本分量类型的出现与任何参考序列中该分量类型的出现之间的匹配或近似匹配，并产生相应的相关信号。 决策电路（31）响应来自所有相关器的相关信号，以提供整个输入序列与任何参考序列之间的匹配或近似匹配的指示。
-
-
-
-
-
-
-
-
-
搜索结果
26 条记录 (耗时 0.011 秒)
