-
公开(公告)号：US08510311B2
公开(公告)日：2013-08-13
申请号：US12170597
申请日：2008-07-10
IPC分类号： G06F17/30
CPC分类号： G06F17/30539 , G06K9/00288 , G06K9/6276
摘要： A pattern search apparatus includes a storage unit, a distribution acquisition unit, a hash function unit, a training unit, and a search unit. A cumulative probability distribution of the training pattern on an arbitrary axis is obtained, and hash function each of which divides a probability value are defined based on the cumulative probability distribution.
摘要翻译： 图案搜索装置包括存储单元，分发获取单元，散列函数单元，训练单元和搜索单元。 获得训练样本在任意轴上的累积概率分布，并且基于累积概率分布来定义每一个划分概率值的散列函数。
-
42.发明授权公开(公告)号：US08224038B2
公开(公告)日：2012-07-17
申请号：US12191027
申请日：2008-08-13
申请人： Hisashi Aoki , Koji Yamamoto , Osamu Yamaguchi , Kenichi Tabe
发明人： Hisashi Aoki , Koji Yamamoto , Osamu Yamaguchi , Kenichi Tabe
IPC分类号： G06K9/00
CPC分类号： G06K9/00711 , G06K9/00295
摘要： When groups of coordinates of face areas respectively contained in mutually different frames are within a predetermined error range, a face attribute assigning unit assigns mutually the same face attribute value to each of the face areas. In the case where a difference in the feature amounts between the frames is within a predetermined error range, a similar shot detecting unit detects that the shots from which the frames have respectively been extracted are similar shots to each of which mutually the same shot attribute value is assigned. In the case where it is judged that face areas that respectively appear in the frames contained in the similar shots and to which mutually different face attribute values have respectively been assigned represent the face of mutually the same person, the face attribute re-assigning unit assigns mutually the same face attribute value to each of the face areas.
摘要翻译： 当分别包含在相互不同的帧中的面部区域的坐标组在预定的误差范围内时，脸部属性分配单元将相同的脸部属性值分配给每个脸部区域。 在帧之间的特征量的差异在预定的误差范围内的情况下，类似的拍摄检测单元检测到已经分别提取了帧的拍摄相似的拍摄，其中相同的拍摄属性值 被分配。 在判断分别出现在相似拍摄中包含的并分别具有相互不同的面部属性值的帧中的脸部区域表示相互相同的人的面部的情况下，脸部属性重新分配单元分配 对每个面部区域相同的脸部属性值。
-
43.发明申请IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND COMPUTER PROGRAM PRODUCT 有权图像处理设备，图像处理方法和计算机程序产品公开(公告)号：US20120063671A1
公开(公告)日：2012-03-15
申请号：US13232710
申请日：2011-09-14
申请人： Miki YAMADA , Osamu Yamaguchi
发明人： Miki YAMADA , Osamu Yamaguchi
IPC分类号： G06K9/00
CPC分类号： G06K9/00248 , G06K9/00899
摘要： According to one embodiment, an image processing device includes an obtaining unit configured to obtain a plurality of images captured in time series; a first calculating unit configured to calculate a first change vector indicating a change between the images in an angle representing a posture of a subject included in each of the images; a second calculating unit configured to calculate a second change vector indicating a change in coordinates of a feature point of the subject; a third calculating unit configured to calculate an intervector angle between the first change vector and the second change vector; and a determining unit configured to determine that the subject is three-dimensional when the intervector angle is smaller than a predetermined first threshold.
摘要翻译： 根据一个实施例，图像处理装置包括：获取单元，被配置为获得以时间序列捕获的多个图像; 第一计算单元，被配置为计算表示每个图像中包括的被摄体的姿势的角度的图像之间的变化的第一变化矢量; 第二计算单元，被配置为计算表示所述被摄体的特征点的坐标变化的第二变化矢量; 第三计算单元，被配置为计算所述第一变化矢量和所述第二变化矢量之间的矢量角; 以及确定单元，被配置为当所述对角角度小于预定的第一阈值时，确定所述被摄体是三维的。
-
公开(公告)号：US08077979B2
公开(公告)日：2011-12-13
申请号：US12401300
申请日：2009-03-10
申请人： Tomokazu Kawahara , Osamu Yamaguchi
发明人： Tomokazu Kawahara , Osamu Yamaguchi
摘要： A pattern recognition method comprises steps of inputting a pattern of a recognition object performing feature extraction from the input pattern to generate a feature vector, increasing the number of quantization in an order from quantization number 1 or quantization number 2 to calculate a quantization threshold of each of the quantization number, wherein the quantization threshold of quantization number (n+1) using a quantization threshold of quantization number n (n>=1) is calculated and a quantization function having a quantization threshold corresponding to quantization number S (S>n) is generated, quantizing each component of the feature vector of the input pattern using the quantization function to generate an input quantization feature vector having each of the quantized component, storing a dictionary feature vector of the recognition object, or a quantized dictionary feature vector in which each component of the dictionary feature vector of the pattern of a recognition object is quantized; calculating a similarity between the input quantization feature vector and the dictionary feature vector, or a similarity between the input quantization feature vector and the quantized dictionary feature vector; and recognizing the recognition object based on the similarity.
摘要翻译： 模式识别方法包括以下步骤：从输入模式输入执行特征提取的识别对象的图案，以生成特征向量，从量化数1或量化数2增加量化数量，以计算每个的量化阈值 ，其中使用量化数n（n> = 1）的量化阈值的量化数量（n + 1）的量化阈值被计算，并且具有对应于量化数S（S> n）的量化阈值的量化函数 ），使用量化函数量化输入图案的特征向量的每个分量，以生成具有每个量化分量，存储识别对象的词典特征向量或量化词典特征向量的输入量化特征向量 字典的每个组成部分的识别对象的图案特征向量 被量化 计算输入量化特征向量和字典特征向量之间的相似度，或输入量化特征向量与量化词典特征向量之间的相似度; 并基于相似度识别识别对象。
-
公开(公告)号：US07987723B2
公开(公告)日：2011-08-02
申请号：US12538211
申请日：2009-08-10
IPC分类号： G01N29/06
CPC分类号： G01N29/225 , B23Q35/10 , G01N2291/2694
摘要： There is provided a copying apparatus that copies a workpiece, includes a shoe that is brought into contact with the workpiece, an air cylinder that enables moving the shoe in a vertical direction, a clamping mechanism that grasps the workpiece from side surfaces placed in a direction orthogonal to a traveling direction and, and a lateral translatory slide guide that slides the clamping mechanism in the direction.
摘要翻译： 提供了复印工件的复印装置，包括与工件接触的鞋，能够使鞋沿垂直方向移动的气缸，夹持机构，该夹紧机构从沿着方向 与行进方向正交的横向平移滑动引导件，以及沿着该方向滑动夹紧机构的横向平移滑动引导件。
-
公开(公告)号：US07660465B2
公开(公告)日：2010-02-09
申请号：US11371655
申请日：2006-03-09
申请人： Osamu Yamaguchi
发明人： Osamu Yamaguchi
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/6211
摘要： A pattern recognition apparatus compares an image including a photographed object to be recognized with a model previously registered in a table and recognizes the object to be recognized, and the pattern recognition apparatus includes an image input part 1, a feature point extraction part 2, a triangulation part 3, a feature point selection part 4, a basis calculation part 5, a partial pattern structure part 6, an index calculation part 7, a table registration part 8, a pattern similarity calculation part 9, a hypothesis information generation part 10, and an object recognition part 11. Plural feature points are extracted from the image of the object to be recognized, triangulation of a feature point set is obtained, and a combination of plural feature points is selected from plural feature points in accordance with the extracted triangulation.
摘要翻译： 图案识别装置将包括要识别的拍摄对象的图像与预先登记在表中的模型进行比较，并识别要识别的对象，并且图案识别装置包括图像输入部1，特征点提取部2， 三角测量部3，特征点选择部4，基础计算部5，部分图案结构部6，索引计算部7，表格登记部8，图案相似度计算部9，假设信息生成部10， 和对象识别部分11.从要识别的对象的图像中提取多个特征点，获得特征点集合的三角测量，并且根据提取的三角测量从多个特征点中选择多个特征点的组合 。
-
公开(公告)号：US20090232399A1
公开(公告)日：2009-09-17
申请号：US12401300
申请日：2009-03-10
申请人： Tomokazu KAWAHARA , Osamu Yamaguchi
发明人： Tomokazu KAWAHARA , Osamu Yamaguchi
摘要： A pattern recognition method comprises steps of inputting a pattern of a recognition object performing feature extraction from the input pattern to generate a feature vector, increasing the number of quantization in an order from quantization number 1 or quantization number 2 to calculate a quantization threshold of each of the quantization number, wherein the quantization threshold of quantization number (n+1) using a quantization threshold of quantization number n (n>=1) is calculated and a quantization function having a quantization threshold corresponding to quantization number S (S>n) is generated, quantizing each component of the feature vector of the input pattern using the quantization function to generate an input quantization feature vector having each of the quantized component, storing a dictionary feature vector of the recognition object, or a quantized dictionary feature vector in which each component of the dictionary feature vector of the pattern of a recognition object is quantized; calculating a similarity between the input quantization feature vector and the dictionary feature vector, or a similarity between the input quantization feature vector and the quantized dictionary feature vector; and recognizing the recognition object based on the similarity.
摘要翻译： 模式识别方法包括以下步骤：从输入模式输入执行特征提取的识别对象的图案，以生成特征向量，从量化数1或量化数2增加量化数量，以计算每个的量化阈值 ，其中使用量化数n（n> = 1）的量化阈值的量化数量（n + 1）的量化阈值被计算，并且具有对应于量化数S（S> n）的量化阈值的量化函数 ），使用量化函数量化输入图案的特征向量的每个分量，以生成具有每个量化分量，存储识别对象的词典特征向量或量化词典特征向量的输入量化特征向量 字典的每个组成部分的识别对象的图案特征向量 被量化 计算输入量化特征向量和字典特征向量之间的相似度，或输入量化特征向量与量化词典特征向量之间的相似度; 并基于相似度识别识别对象。
-
公开(公告)号：US07454062B2
公开(公告)日：2008-11-18
申请号：US10980310
申请日：2004-11-04
IPC分类号： G06K9/00
CPC分类号： G06K9/6247
摘要： In one embodiment of the invention, a pattern recognition apparatus comprises a unit for inputting a pattern of a to-be recognized category; and a processor with a memory for: generating input subspace; calculating and storing reference subspaces; storing constraint subspaces for extracting features; projecting the input subspace and the reference subspaces respectively onto the constraint subspaces; calculating similarities between the respective reference subspaces and the input subspace in such projected state; combining the similarities in respect of the constraint subspaces on each of the reference subspaces; and identifying the to-be recognized category with a category corresponding to one of the reference subspaces, if the combined similarity between the one of reference subspace and the input subspace is highest among them.
摘要翻译： 在本发明的一个实施例中，模式识别装置包括用于输入被识别类别的模式的单元; 以及具有用于产生输入子空间的存储器的处理器; 计算和存储参考子空间; 存储用于提取特征的约束子空间; 将输入子空间和参考子空间分别投影到约束子空间上; 在这种预计状态下计算相应参考子空间和输入子空间之间的相似度; 结合每个参考子空间上的约束子空间的相似性; 并且如果参考子空间和输入子空间中的一个之间的组合相似度在它们之中最高，则识别具有与一个参考子空间相对应的类别的被识别类别。
-
49.发明授权Pattern recognition apparatus and method using distributed model representation of partial images 失效使用部分图像的分布式模型表示的模式识别装置和方法公开(公告)号：US07200270B2
公开(公告)日：2007-04-03
申请号：US10316097
申请日：2002-12-11
申请人： Osamu Yamaguchi
发明人： Osamu Yamaguchi
IPC分类号： G06K9/62
CPC分类号： G06K9/6211
摘要： Pattern recognition apparatus and method for recognizing a recognition object by comparing with pre-registered models. From an inputted image, multiple feature points are extracted; therefrom, combination of multiple feature points is selected; and from the multiple selected feature points, bases which represent the positions and positional relations of these feature points are calculated. A partial pattern of the recognition object corresponding to each of the calculated bases is extracted from the image; and a search place on the table is decided based on an invariant parameter to geometric transformation of the partial pattern. The similarity between the partial pattern of the model registered in the search place on the table and the partial pattern of the recognition object is judged; and a plurality of hypothesis information showing that the recognition object exists in the image is generated based on the similarity between both partial patterns. The identification, position etc are decided based on the information.
摘要翻译： 通过与预先注册的模型进行比较来识别识别对象的模式识别装置和方法。 从输入的图像中提取多个特征点; 从中选择多个特征点的组合; 并且从多个选择的特征点中，计算表示这些特征点的位置和位置关系的基底。 从图像中提取对应于每个计算的基数的识别对象的部分图案; 并且基于部分模式的几何变换的不变参数来决定表上的搜索位置。 判断登记在桌子上的搜索位置的模型的部分模式与识别对象的部分模式之间的相似度; 并且基于两个部分模式之间的相似度生成表示图像中存在识别对象的多个假设信息。 识别，职位等是根据信息决定的。
-
公开(公告)号：US20060115125A1
公开(公告)日：2006-06-01
申请号：US11334383
申请日：2006-01-19
申请人： Mayumi Yuasa , Kazuhiro Fukui , Osamu Yamaguchi
发明人： Mayumi Yuasa , Kazuhiro Fukui , Osamu Yamaguchi
IPC分类号： G06K9/00
CPC分类号： G06K9/00805 , G06T7/74
摘要： An image input unit inputs an image including a user's face area to specify the user's gaze or face direction. A pattern generation unit generates an input pattern that can be compared with each dictionary pattern from the image. A dictionary unit previously stores a plurality of dictionary patterns each of which differently corresponds to the user's gaze or face direction. A pattern comparison unit respectively calculates a similarity degree between the input pattern and each of the dictionary patterns by comparing the input pattern with each of the dictionary patterns. A gaze detection unit detects the user's gaze or face direction based on the similarity degree.
-
-
-
-
-
-
-
-
-
搜索结果
100 条记录 (耗时 0.032 秒)
