专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO1992008204A2 METHOD OF DETECTING AND ESTIMATING THE POSITION IN SPACE OF OBJECTS FROM A TWO-DIMENSIONAL IMAGE 审中-公开
标题翻译：从二维图像中检测和估计物体空间位置的方法
公开(公告)号：WO1992008204A2
公开(公告)日：1992-05-14
申请号：PCT/DE1991000775
申请日：1991-10-02
申请人： SIEMENS AKTIENGESELLSCHAFT , WIRTZ, Brigitte , MAGGIONI, Christoph
发明人： SIEMENS AKTIENGESELLSCHAFT
IPC分类号： G06K09/66
CPC分类号： G06K9/32 , G06K9/00201 , G06K9/6251 , G06T7/50 , G06T2207/20084
摘要： The invention uses adaptive vector quantization to detect three-dimensional objects and to estimate their spatial-position coordinates from the two-dimensional coordinates of feature points obtained, by digital image processing, from a two-dimensional image of the three-dimensional objects. To this end, a special learning process and a special object-detection process are described. The invention has wide fields of application in the video-based operation of automated production facilities.
摘要翻译：本发明使用自适应矢量量化来检测三维物体，并且通过数字图像处理从三维物体的二维图像获得的特征点的二维坐标来估计它们的空间位置坐标。为此，描述了特殊的学习过程和特殊的对象检测过程。本发明在自动化生产设备的视频操作中具有广泛的应用领域。

2. 发明申请

WO1992014200A1 PREDICTIVE SELF-ORGANIZING NEURAL NETWORK 审中-公开
标题翻译：预测自组织神经网络
公开(公告)号：WO1992014200A1
公开(公告)日：1992-08-20
申请号：PCT/US1992000793
申请日：1992-01-30
申请人： TRUSTEES OF BOSTON UNIVERSITY
发明人： TRUSTEES OF BOSTON UNIVERSITY , CARPENTER, Gail, A. , GROSSBERG, Stephen , REYNOLDS, John, H.
IPC分类号： G06K09/66
CPC分类号： G06K9/6222 , G06N3/0409
摘要： An A pattern recognition subsystem responds to an A feature representation input to select an A-category-representation and predict a B-category-representation and its associated B feature representation input. During learning trials, a predicted B-category-representation is compared to that obtained through a B pattern recognition subsystem. With mismatch, a vigilance parameter of the A-pattern-recognition subsystem is increased to cause reset of the first-category-representation selection. Inputs to the pattern recognition subsystems may be preprocessed to complement code the inputs.

3. 发明申请

WO1991017520A1 NEURAL NETWORK WITH BACK PROPAGATION CONTROLLED THROUGH AN OUTPUT CONFIDENCE MEASURE 审中-公开
标题翻译：通过输出信心测量来控制反向传播的神经网络
公开(公告)号：WO1991017520A1
公开(公告)日：1991-11-14
申请号：PCT/US1991003003
申请日：1991-05-01
申请人： EASTMAN KODAK COMPANY
发明人： EASTMAN KODAK COMPANY , GABORSKI, Roger, Stephen
IPC分类号： G06K09/66
CPC分类号： G06K9/66 , G06N3/084
摘要： Neural network, particularly one suited for use in optical character recognition (OCR) systems, which through controlling back propagation and adjustment of neural weight and bias values through an output confidence measure, smoothly, rapidly and accurately adapts its response to actual changing input data (characters). Specifically, the results of appropriate actual unknown input characters, which have been recognized with an output confidence measure that lies within a pre-defined range, are used to adaptively re-train the network during pattern recognition. By limiting the maximum value of the output confidence measure at which this re-training will occur, the network re-trains itself only when the input characters have changed by a sufficient margin from initial training data such that this re-training is likely to produce a subsequent noticeable increase in the recognition accuracy provided by the network. Output confidence is measured as a ratio between the highest and next highest values produced by output neurons in the network.
摘要翻译：神经网络，特别适用于光学字符识别（OCR）系统，其通过控制反向传播和通过输出置信度测量来调整神经重量和偏差值，平滑，快速和准确地将其响应适应于实际改变的输入数据（OCR）字符）。具体地说，在模式识别期间，使用已经用位于预定义范围内的输出置信度量来识别的适当的实际未知输入字符的结果被用于自适应地重新训练网络。通过限制出现这种重新训练的输出置信度量的最大值，只有当输入字符从初始训练数据改变了足够的余量以后，网络才能自动重新训练，以便这种再培训可能产生网络提供的识别精度随后明显增加。输出置信度被测量为由网络中的输出神经元产生的最高和最高值之间的比率。

4. 发明申请

WO1992020038A1 METHOD AND DEVICE FOR AUTOMATIC OBJECT CLASSIFICATION 审中-公开
标题翻译：自动对象分类的方法和装置
公开(公告)号：WO1992020038A1
公开(公告)日：1992-11-12
申请号：PCT/FR1992000349
申请日：1992-04-17
申请人： THOMSON-CSF , QUIGNON, Jean , REGEF, Jean-Luc
发明人： THOMSON-CSF
IPC分类号： G06K09/66
CPC分类号： G06K9/6281 , G06N3/10
摘要： Method and device for the automatic classification of objects, comprising an apprenticeship phase and an execution phase, combining in the apprenticeship phase a self-organization method with the gradient back-propagation method, and implementing the execution phase according to the perceptron structure. Application: recognition of shapes for robotics or indutrial control.

5. 发明申请

WO1989002134A1 APPARATUS FOR PATTERN RECOGNITION 审中-公开
标题翻译：用于图案识别的装置
公开(公告)号：WO1989002134A1
公开(公告)日：1989-03-09
申请号：PCT/GB1988000710
申请日：1988-08-26
申请人： BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY , TATTERSALL, Graham, David
发明人： BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY
IPC分类号： G06K09/66
CPC分类号： G10L15/16 , G06K9/64 , G06K9/66 , G06N3/04 , G06N3/063 , G10L15/00
摘要： A temporal sequence of signal vectors X (e.g. generated from a speech signal) is supplied in parallel to elements (101) in an array each of which (after training of the array) provide an output eta indicating the vector's similarity to a reference vector. Persistence is (115) built into the elements so that signals forming a ''trajectory'' within the array, corresponding to an input sequence are simultaneously available for recognition (unit 110 or, preferably by a further such array). Arrays may be cascaded to allow for longer sequences.
摘要翻译：信号矢量X的时间序列（例如，从语音信号产生）被并行地提供给阵列中的每个元素（101）（在阵列的训练之后）提供指示矢量与参考矢量的相似性的输出eta。持久性是（115）内置在元素中，使得在阵列内形成对应于输入序列的“轨迹”的信号同时可用于识别（单元110或优选地通过另外的这种阵列）。阵列可以级联以允许更长的序列。

6. 发明申请

WO1995024017A2 A TOP DOWN PREPROCESSOR FOR A MACHINE VISION SYSTEM 审中-公开
标题翻译：机器视觉系统的顶级预处理器
公开(公告)号：WO1995024017A2
公开(公告)日：1995-09-08
申请号：PCT/US1995002392
申请日：1995-03-02
申请人： THE UNITED STATES OF AMERICA, represented by THE SECRETARY, DEPARTMENT OF HEALTH AND HUMAN SERVICES NATIONAL INSTITUTES OF HEALTH
发明人： THE UNITED STATES OF AMERICA, represented by THE SECRETARY, DEPARTMENT OF HEALTH AND HUMAN SERVICES NATIONAL INSTITUTES OF HEALTH , VOGL, Thomas, P. , BLACKWELL, Kim, T. , ALKON, Daniel, L.
IPC分类号： G06K09/66
CPC分类号： G06K9/4628
摘要： An image recognition and classification system includes a preprocessor in which a "top-down" method is used to extract features from an image; an associative learning neural network system, which groups the features into patterns and classifies the patterns; and a feedback mechanism which improves system performance by tuning preprocessor scale, feature detection, and feature selection.
摘要翻译：图像识别和分类系统包括其中使用“自顶向下”方法从图像中提取特征的预处理器; 关联学习神经网络系统，将特征组合成模式并对模式进行分类; 以及通过调整预处理器规模，特征检测和特征选择来提高系统性能的反馈机制。

7. 发明申请

WO1988010476A1 SYSTEM FOR CATEGORY RECOGNITION OF ANALOG PATTERN 审中-公开
标题翻译：类别识别模拟模式的系统
公开(公告)号：WO1988010476A1
公开(公告)日：1988-12-29
申请号：PCT/US1988001962
申请日：1988-06-09
申请人： BOSTON UNIVERSITY
发明人： BOSTON UNIVERSITY , CARPENTER, Gail, A. , GROSSBERG, Stephen
IPC分类号： G06K09/66
CPC分类号： G06K9/4628 , G06N3/0409
摘要： A neural network includes a feature representation field which receives input patterns. Signals from the feature representation field select a category from a category representation field through a first adaptive filter. Based on the selected category, a template pattern is applied to the feature representation field, and a match between the template and the input is determined. If the angle between the template vector and a vector within the representation field is too great, the selected category is reset. Otherwise the category selection and template pattern are adapted to the input pattern as well as the previously stored template. A complex representation field includes signals normalized relative to signals across the field and feedback for pattern contrast enhancement.

8. 发明申请

WO1998027511A1 METHOD AND DEVICE FOR DETECTING IMAGE CHARACTERISTICS IRRESPECTIVE OF LOCATION OR SIZE 审中-公开
标题翻译：方法和设备的图像的特性本地和尺寸独立的检测
公开(公告)号：WO1998027511A1
公开(公告)日：1998-06-25
申请号：PCT/DE1997002975
申请日：1997-12-18
申请人： KNITTEL, Jochen , GEIGER, Hans
发明人： KNITTEL, Jochen
IPC分类号： G06K09/66
CPC分类号： G06K9/66
摘要： The present invention relates to a method and device for detecting image characteristics irrespective of location or size. Characteristics are extracted from the digitized graphic data by several signal-generating devices and subsequently summarized into complex characteristics combinations on the basis of the relative reciprocal locations. The location-related data, which refers to given characteristics combinations, is computed and forms a characteristics vector value that is independent from location and size and is used to identify the object or to recognize characteristics, i.e. by comparison with previously received reference values.
摘要翻译：本发明涉及用于从图像中的位置和特征的大小独立的检测的方法。从数字化的图像数据特性是由多个信号产生装置，然后将其概括的提取，考虑到它们的相对相互位置为特征的复杂组合。有关的特征的特定组合的位置相关的数据被相加并形成特征向量，其被用来识别所述对象或特征检测的位置和大小无关的值，例如通过与以前获得的参考值进行比较。

9. 发明申请

WO1990011577A1 PATTERN RECOGNITION 审中-公开
标题翻译：模式识别
公开(公告)号：WO1990011577A1
公开(公告)日：1990-10-04
申请号：PCT/GB1990000443
申请日：1990-03-22
申请人： BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY , TATTERSALL, Graham, David
发明人： BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY
IPC分类号： G06K09/66
CPC分类号： G06K9/66 , H04B3/231
摘要： Input values are digitally represented (10) and the bits used to address memories (12). A composite (e.g. the sum) of the memory outputs is formed, and update control (13) is used during ''learning'' to modify the memory contents. The digital representation is formed by an encoder (14) which encodes input values using a redundant code, which preferably has a Hamming distance to signal distance relationship which has a relatively steep initial slope and is closer to being monotonic than is the relationship for a simple binary code.
摘要翻译：输入值以数字方式表示（10）和用于寻址存储器（12）的位。形成存储器输出的复合（例如和），并且在“学习”期间使用更新控制（13）来修改存储器内容。数字表示由编码器（14）形成，编码器（14）使用冗余码对输入值进行编码，其优选地具有与信号距离关系的汉明距离，该距离关系具有相对较陡的初始斜率，并且比简单的关系更接近于单调二进制代码。

10. 发明申请

WO1987003399A1 PATTERN RECOGNITION SYSTEM 审中-公开
标题翻译：模式识别系统
公开(公告)号：WO1987003399A1
公开(公告)日：1987-06-04
申请号：PCT/US1986002553
申请日：1986-11-26
申请人： THE TRUSTEES OF BOSTON UNIVERSITY , CARPENTER, Gail, A. , GROSSBERG, Stephen
发明人： THE TRUSTEES OF BOSTON UNIVERSITY
IPC分类号： G06K09/66
CPC分类号： G06K9/6222
摘要： A self-categorizing pattern recognition system includes an adaptive filter for selecting a category in response to an input pattern. A template is then generated in response to the selected category and a coincident pattern indicating the intersection between the expected pattern and the input pattern is generated. The ratio between the number of elements in the coincident pattern to the number of elements in the input pattern determines whether the category is reset. If the category is not reset, the adaptive filter and template may be modified in response to the coincident pattern. Reset of the selected category is inhibited if no expected pattern is generated. Weighting of the adaptive filter in response to a coincident pattern is inversely related to the number of elements in the input pattern. The selected categories reset where a reset function is less than a vigilance parameter which may be varied in response to teaching events.
摘要翻译：自分类模式识别系统包括用于响应于输入模式选择类别的自适应滤波器。然后响应于所选择的类别生成模板，并且生成指示预期图案和输入图案之间的交点的重合图案。重合模式中的元素数与输入模式中的元素数之间的比率决定了类别是否被重置。如果该类别不被重置，则可以响应于重合模式来修改自适应滤波器和模板。如果不产生预期的模式，则禁止所选类别的复位。响应于一致的图案的自适应滤波器的权重与输入图案中的元素的数量成反比。所选择的类别在复位功能小于可响应于教学事件而改变的警戒参数的情况下重置。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式