-
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。
-
公开(公告)号：US20050141767A1
公开(公告)日：2005-06-30
申请号：US10980310
申请日：2004-11-04
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。
-
公开(公告)号：US08116534B2
公开(公告)日：2012-02-14
申请号：US11754030
申请日：2007-05-25
IPC分类号： G06K9/00
CPC分类号： G06K9/00255 , G06K9/00261 , G06K9/6255
摘要： A face recognition apparatus includes an image sequence acquiring unit, a face image acquiring unit, an intra-sequence classifying unit, an inter-sequence classifying unit, an identification unit, and a reference image storing unit. A plurality of cameras are attached in a corridor for monitoring one place with these cameras, so that when a plurality of moving people pass through, identification is performed for each moving people. Face images are classified into fragmental face image sets, and the fragmental face image sets are classified into integrated sets to achieve the identification.
摘要翻译： 面部识别装置包括图像序列获取单元，面部图像获取单元，序列内分类单元，序列间分类单元，识别单元和参考图像存储单元。 多个摄像机被安装在走廊中用于监视这些照相机的一个位置，使得当多个移动的人通过时，对每个移动的人进行识别。 脸部图像被分类为片段面部图像集，并且将碎片面部图像集合分类为集成集合以实现识别。
-
公开(公告)号：US20070065015A1
公开(公告)日：2007-03-22
申请号：US11516767
申请日：2006-09-07
申请人： Masashi Nishiyama , Osamu Yamaguchi
发明人： Masashi Nishiyama , Osamu Yamaguchi
CPC分类号： G06K9/00208 , G06K9/00221 , G06K9/4661
摘要： An object recognition apparatus in an embodiment includes an image input unit, an object detection unit, a diffuse reflection image generation unit, an object model storage unit, a difference image generation unit, a weight calculation unit, a weighted Gaussian filter application unit, a filter processing unit, and an identification unit. A weight to be assigned to a weighted Gaussian filter is determined in view of variations in lighting conditions and reflection components of pixels of an input image.
摘要翻译： 实施例中的物体识别装置包括图像输入单元，物体检测单元，漫反射图像生成单元，对象模型存储单元，差分图像生成单元，权重计算单元，加权高斯滤波器应用单元， 过滤处理单元和识别单元。 鉴于照明条件的变化和输入图像的像素的反射分量，确定要分配给加权高斯滤波器的权重。
-
公开(公告)号：US20090110303A1
公开(公告)日：2009-04-30
申请号：US12262735
申请日：2008-10-31
CPC分类号： G06K9/36 , G06K9/00228 , G06T5/003 , G06T2207/20081 , G06T2207/30201
摘要： An object is identified by detecting an object area image of an object to be recognized from a degraded image, converting the object area image to a frequency area, extracting a feature vector which indicates the amount of blur, comparing the feature vector and a classified plurality of blurred images, obtaining a cluster which is the most similar to the feature vector, selecting one point spread function corresponding to the similar cluster, restoring the object area image to the image before being blurred using the point spread function, and comparing the restored image and a target image.
摘要翻译： 通过从劣化图像检测要识别的对象的对象区域图像来识别对象，将对象区域图像转换为频率区域，提取指示模糊量的特征向量，比较特征向量和分类多个 模糊图像，获得与特征向量最相似的簇，选择与类似簇对应的一个点扩展函数，使用点扩散函数将对象区域图像恢复到模糊之前的图像，以及比较恢复的图像 和目标图像。
-
公开(公告)号：US20070297652A1
公开(公告)日：2007-12-27
申请号：US11754030
申请日：2007-05-25
IPC分类号： G06K9/00
CPC分类号： G06K9/00255 , G06K9/00261 , G06K9/6255
摘要： A face recognition apparatus includes an image sequence acquiring unit, a face image acquiring unit, an intra-sequence classifying unit, an inter-sequence classifying unit, an identification unit, and a reference image storing unit. A plurality of cameras are attached in a corridor for monitoring one place with these cameras, so that when a plurality of moving people pass through, identification is performed for each moving people. Face images are classified into fragmental face image sets, and the fragmental face image sets are classified into integrated sets to achieve the identification.
摘要翻译： 面部识别装置包括图像序列获取单元，面部图像获取单元，序列内分类单元，序列间分类单元，识别单元和参考图像存储单元。 多个摄像机被安装在走廊中用于监视这些照相机的一个位置，使得当多个移动的人通过时，对每个移动的人进行识别。 脸部图像被分类为片段面部图像集，并且将碎片面部图像集合分类为集成集合以实现识别。
-
公开(公告)号：US07346192B2
公开(公告)日：2008-03-18
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.
摘要翻译： 图像输入单元输入包括用户脸部区域的图像以指定用户的注视或脸部方向。 图案生成单元生成可以与来自图像的每个字典图案进行比较的输入图案。 字典单元预先存储多个字典模式，每个字典模式与用户的注视或面部方向不同地对应。 图案比较单元通过将输入图案与每个字典图案进行比较来分别计算输入图案和每个字典图案之间的相似度。 注视检测单元基于相似度检测用户的注视或面部方向。
-
8.发明授权公开(公告)号：US07330591B2
公开(公告)日：2008-02-12
申请号：US10372312
申请日：2003-02-25
申请人： Kazuhiro Fukui , Osamu Yamaguchi
发明人： Kazuhiro Fukui , Osamu Yamaguchi
IPC分类号： G06K9/46
CPC分类号： G06K9/00288 , G06K9/64 , Y10S707/99936
摘要： The present invention solves an eigenvalue problem using a sum of projection matrixes for each subspace. A space which is spanned by a plurality of eigenvectors which are selected starting from those having a smaller eigenvalue is used as a constraint subspace.
摘要翻译： 本发明使用每个子空间的投影矩阵的和来求解特征值问题。 使用从具有较小特征值的那些开始选择的多个特征向量所跨越的空间被用作约束子空间。
-
公开(公告)号：US06690814B1
公开(公告)日：2004-02-10
申请号：US09522597
申请日：2000-03-10
IPC分类号： G06K900
CPC分类号： G06K9/00228
摘要： An image processing apparatus. A camera inputs an image of a face of a person to be recognized. A recognition area detection section generates a difference image between the input image and a predetermined pattern, and detects a recognition area whose value is above a threshold from the input image. An input data generation section converts the recognition area to a predetermined input data. A similarity calculation section calculates a similarity by comparing the predetermined input data with a predetermined dictionary data. A view position of the camera is located lower than a position of the face of the person. A direction of the optical axis of the camera represents an angle of elevation from a horizontal direction.
-
公开(公告)号：US06466685B1
公开(公告)日：2002-10-15
申请号：US09352839
申请日：1999-07-13
申请人： Kazuhiro Fukui , Kaoru Suzuki , Osamu Yamaguchi , Kenichi Maeda
发明人： Kazuhiro Fukui , Kaoru Suzuki , Osamu Yamaguchi , Kenichi Maeda
IPC分类号： G06K900
CPC分类号： G06K9/00288
摘要： An image pattern of an object is inputted. An input subspace calculation section calculates an input subspace from the image pattern. A dictionary subspace calculation section calculates a dictionary subspace from a learning pattern of each object. A constraint subspace calculation means calculates a constraint subspace from a plurality of input subspaces previously calculated according to constraints to suppress unnecessary patterns. A projection section projects the input subspace and the dictionary subspace onto the constraint subspace. A recognition section recognizes the object by comparing the projected input subspace with the projected dictionary subspace.
摘要翻译： 输入物体的图像图案。 输入子空间计算部分根据图像模式计算输入子空间。 字典子空间计算部分从每个对象的学习模式计算字典子空间。 约束子空间计算装置从先前根据约束计算的多个输入子空间计算约束子空间以抑制不必要的模式。 投影部分将输入子空间和字典子空间投影到约束子空间上。 识别部通过将投影的输入子空间与投影的字典子空间进行比较来识别对象。
-
-
-
-
-
-
-
-
-
搜索结果
100 条记录 (耗时 0.027 秒)
