公开(公告)号：US20120230546A1

公开(公告)日：2012-09-13

申请号：US13508850

申请日：2011-09-09

申请人： Yang Hua ,  Shuicheng Yan ,  Zhongyang Huang ,  Sheng Mei Shen ,  Ryouichi Kawanishi

发明人： Yang Hua ,  Shuicheng Yan ,  Zhongyang Huang ,  Sheng Mei Shen ,  Ryouichi Kawanishi

IPC分类号： G06K9/62

CPC分类号： G06K9/00677

摘要： The present invention provides an image recognition apparatus with enhanced performance and robustness.In an image recognition apparatus 1, an image classification information accumulating unit 20 stores therein feature information defining visual features of various objects obtained through a learning process. For classification of input images, an image feature obtaining unit 18 extracts descriptors indicating features from each input image, image vocabularies corresponding to the descriptors are voted, and a classifying unit 19 calculates existence probabilities of one or more candidate objects, based on the result of the voting. According to the existence probabilities, objects contained in the image is identified. Through the calculation, the existence probabilities are adjusted by an exclusive classifier, based on exclusive relationship information defining exclusive object sets each containing different objects (object labels) predicted not to coexist in a same image.

摘要翻译： 本发明提供了具有增强的性能和鲁棒性的图像识别装置。 在图像识别装置1中，图像分类信息存储单元20存储定义通过学习处理获得的各种对象的视觉特征的特征信息。 为了输入图像的分类，图像特征获取单元18从每个输入图像中提取指示特征的描述符，并且对与描述符相对应的图像词汇进行表示，并且分类单元19基于以下结果计算一个或多个候选对象的存在概率 投票。 根据存在概率，识别图像中包含的对象。 通过计算，存在概率由排他分类器基于排除关系信息进行调整，该专属关系信息定义了包含不同于同一图像中不共存的不同对象（对象标签）的排他对象集合。

公开(公告)号：US08687851B2

公开(公告)日：2014-04-01

申请号：US13508850

申请日：2011-09-09

申请人： Yang Hua ,  Shuicheng Yan ,  Zhongyang Huang ,  Sheng Mei Shen ,  Ryouichi Kawanishi

发明人： Yang Hua ,  Shuicheng Yan ,  Zhongyang Huang ,  Sheng Mei Shen ,  Ryouichi Kawanishi

IPC分类号： G06K9/00

CPC分类号： G06K9/00677

摘要： The present invention provides an image recognition apparatus with enhanced performance and robustness.In an image recognition apparatus 1, an image classification information accumulating unit 20 stores therein feature information defining visual features of various objects obtained through a learning process. For classification of input images, an image feature obtaining unit 18 extracts descriptors indicating features from each input image, image vocabularies corresponding to the descriptors are voted, and a classifying unit 19 calculates existence probabilities of one or more candidate objects, based on the result of the voting. According to the existence probabilities, objects contained in the image is identified. Through the calculation, the existence probabilities are adjusted by an exclusive classifier, based on exclusive relationship information defining exclusive object sets each containing different objects (object labels) predicted not to coexist in a same image.

摘要翻译： 本发明提供了具有增强的性能和鲁棒性的图像识别装置。 在图像识别装置1中，图像分类信息存储单元20存储定义通过学习处理获得的各种对象的视觉特征的特征信息。 为了输入图像的分类，图像特征获取单元18从每个输入图像中提取指示特征的描述符，并且对与描述符相对应的图像词汇进行表示，并且分类单元19基于以下结果计算一个或多个候选对象的存在概率 投票。 根据存在概率，识别图像中包含的对象。 通过计算，存在概率由排他分类器基于排除关系信息进行调整，该专属关系信息定义了包含不同于同一图像中不共存的不同对象（对象标签）的排他对象集合。

公开(公告)号：US08897578B2

公开(公告)日：2014-11-25

申请号：US13817631

申请日：2012-08-29

申请人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

发明人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

IPC分类号： G06K9/62 ,  G06K9/34 ,  G06K9/74 ,  G06T7/00 ,  G06K9/46

CPC分类号： G06T7/0081 ,  G06K9/4642 ,  G06K9/4676

摘要： An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

摘要翻译： 一种图像识别装置，通过减少通过通用对象识别在目标被识别的对象的位置，大小，背景杂波等的影响，与传统技术相比，提高了通用对象识别的准确性。 图像识别装置执行通用对象识别，包括：分割单元，被配置为根据从输入图像的内容中提取的含义将输入图像分割成多个区域; 生成单元，被配置为计算所述多个区域中的每一个的特征数据，并且生成反映所计算的特征数据的所述输入图像的特征数据; 以及检查单元，被配置为根据输入图像的特征数据来检查输入图像中是否存在识别对象物体。

公开(公告)号：US20130071031A1

公开(公告)日：2013-03-21

申请号：US13700241

申请日：2012-04-04

申请人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

发明人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

IPC分类号： G06K9/46

CPC分类号： G06K9/46 ,  G11B27/034 ,  H04N5/76

摘要： The present invention provides an image processing device capable of combining a plurality of contents (e.g. videos) with a story line retained as much as possible, while reducing view's discomfort. The image processing device compares one of the contents, which contains a first partial content and a second partial content subsequent to the first partial content, with another one of the contents, which contains a plurality of consecutive partial contents, so as to detect, as a third partial content, a partial content with the highest similarity value from among the plurality of partial contents, and generates relational information by using the highest similarity value obtained by the first processing unit, the relational information being used for merging the first partial content, the second partial content and the third partial content.

摘要翻译： 本发明提供一种图像处理装置，其能够将多个内容（例如视频）与尽可能保留的故事线组合，同时减少视图的不适。 图像处理装置将包含第一部分内容和第一部分内容之后的第二部分内容的内容之一与包含多个连续部分内容的内容中的另一个进行比较，以便检测为 第三部分内容，来自所述多个部分内容中具有最高相似度值的部分内容，并且通过使用由所述第一处理单元获得的最高相似度值生成关系信息，所述关系信息用于合并所述第一部分内容， 第二部分内容和第三部分内容。

公开(公告)号：US08958646B2

公开(公告)日：2015-02-17

申请号：US13700241

申请日：2012-04-04

申请人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

发明人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

IPC分类号： G06K9/46 ,  G06K9/66 ,  G11B27/034 ,  H04N5/76

CPC分类号： G06K9/46 ,  G11B27/034 ,  H04N5/76

摘要： An image processing device combines a plurality of contents (e.g. videos) with a story line retained as much as possible, while reducing view's discomfort. The image processing device compares one of the contents, which contains a first partial content and a second partial content subsequent to the first partial content, with another one of the contents, which contains a plurality of consecutive partial contents; detects, as a third partial content, a partial content with the highest similarity value from among the plurality of partial contents; and generates relational information by using the highest similarity value obtained by the first processing unit. The relational information is then used for merging the first partial content, the second partial content and the third partial content.

摘要翻译： 图像处理装置将多个内容（例如视频）与尽可能保留的故事线相结合，同时减少视图的不适。 图像处理装置将包含第一部分内容和第一部分内容之后的第二部分内容的内容之一与包含多个连续部分内容的内容中的另一个进行比较; 从所述多个部分内容中检测具有最高相似度值的部分内容作为第三部分内容; 并且通过使用由第一处理单元获得的最高相似度值来生成关系信息。 关系信息然后用于合并第一部分内容，第二部分内容和第三部分内容。

公开(公告)号：US20140193074A1

公开(公告)日：2014-07-10

申请号：US13817631

申请日：2012-08-29

申请人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

发明人： Zhongyang Huang ,  Yang Hua ,  Shuicheng Yan ,  Qiang Chen ,  Ryouichi Kawanishi

IPC分类号： G06T7/00

CPC分类号： G06T7/0081 ,  G06K9/4642 ,  G06K9/4676

摘要： An image recognition device that improves the accuracy of generic object recognition compared with conventional technologies by reducing the influence of the position, size, background clutter and the like of an object that is targeted to be recognized in the input image by the generic object recognition. The image recognition device performs a generic object recognition and includes: a segmenting unit configured to segment an input image into a plurality of regions in accordance with meanings extracted from content of the input image; a generating unit configured to compute feature data for each of the plurality of regions and generate feature data of the input image reflecting the computed feature data; and a checking unit configured to check whether or not a recognition-target object is present in the input image in accordance with the feature data of the input image.

摘要翻译： 一种图像识别装置，通过减少通过通用对象识别在目标被识别的对象的位置，大小，背景杂波等对传统技术的准确性而提高通用对象识别的精度。 图像识别装置执行通用对象识别，包括：分割单元，被配置为根据从输入图像的内容中提取的含义将输入图像分割成多个区域; 生成单元，被配置为计算所述多个区域中的每一个的特征数据，并且生成反映所计算的特征数据的所述输入图像的特征数据; 以及检查单元，被配置为根据输入图像的特征数据来检查输入图像中是否存在识别对象物体。

公开(公告)号：US20090052748A1

公开(公告)日：2009-02-26

申请号：US12194467

申请日：2008-08-19

申请人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

发明人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

IPC分类号： G06K9/00 ,  G06K9/36

CPC分类号： G06K9/00288 ,  G06K9/00208

摘要： A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

摘要翻译： 提供了一种用于从2D图像生成面部的3D图像的方法和系统，用于在3D图像的不同图像条件下生成面部的2D图像，并且基于所生成的2D图像来识别目标面部的2D图像。 识别系统提供了一种面部的3D模型，其包括在标准图像条件下的标准面的3D图像和指示单个脸部与标准脸部的变化的参数。 为了生成面部的3D图像，识别系统在标准图像条件下输入面部的2D图像。 识别系统然后计算将2D图像的点映射到标准面的2D图像的对应点的参数。 识别系统使用这些参数与3D模型在不同图像条件下生成脸部的3D图像。

公开(公告)号：US20060245639A1

公开(公告)日：2006-11-02

申请号：US11118116

申请日：2005-04-29

申请人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

发明人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K9/00208

摘要： A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

摘要翻译： 提供了一种用于从2D图像生成面部的3D图像的方法和系统，用于在3D图像的不同图像条件下生成面部的2D图像，并且基于所生成的2D图像来识别目标面部的2D图像。 识别系统提供了一种面部的3D模型，其包括在标准图像条件下的标准面的3D图像和指示单个脸部与标准脸部的变化的参数。 为了生成面部的3D图像，识别系统在标准图像条件下输入面部的2D图像。 识别系统然后计算将2D图像的点映射到标准面的2D图像的对应点的参数。 识别系统使用这些参数与3D模型在不同图像条件下生成脸部的3D图像。

公开(公告)号：US07646909B2

公开(公告)日：2010-01-12

申请号：US12194467

申请日：2008-08-19

申请人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

发明人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K9/00208

摘要： A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

摘要翻译： 提供了一种用于从2D图像生成面部的3D图像的方法和系统，用于在3D图像的不同图像条件下生成面部的2D图像，并且基于所生成的2D图像来识别目标面部的2D图像。 识别系统提供了一种面部的3D模型，其包括在标准图像条件下的标准面的3D图像和指示单个脸部与标准脸部的变化的参数。 为了生成面部的3D图像，识别系统在标准图像条件下输入面部的2D图像。 识别系统然后计算将2D图像的点映射到标准面的2D图像的对应点的参数。 识别系统使用这些参数与3D模型在不同图像条件下生成脸部的3D图像。

公开(公告)号：US07415152B2

公开(公告)日：2008-08-19

申请号：US11118116

申请日：2005-04-29

申请人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

发明人： Dalong Jiang ,  Hong-Jiang Zhang ,  Lei Zhang ,  Shuicheng Yan ,  Yuxiao Hu

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K9/00208

摘要： A method and system for generating 3D images of faces from 2D images, for generating 2D images of the faces at different image conditions from the 3D images, and for recognizing a 2D image of a target face based on the generated 2D images is provided. The recognition system provides a 3D model of a face that includes a 3D image of a standard face under a standard image condition and parameters indicating variations of an individual face from the standard face. To generate the 3D image of a face, the recognition system inputs a 2D image of the face under a standard image condition. The recognition system then calculates parameters that map the points of the 2D image to the corresponding points of a 2D image of the standard face. The recognition system uses these parameters with the 3D model to generate 3D images of the face at different image conditions.

摘要翻译： 提供了一种用于从2D图像生成面部的3D图像的方法和系统，用于在3D图像的不同图像条件下生成面部的2D图像，并且基于所生成的2D图像来识别目标面部的2D图像。 识别系统提供了一种面部的3D模型，其包括在标准图像条件下的标准面的3D图像和指示单个脸部与标准脸部的变化的参数。 为了生成面部的3D图像，识别系统在标准图像条件下输入面部的2D图像。 识别系统然后计算将2D图像的点映射到标准面的2D图像的对应点的参数。 识别系统使用这些参数与3D模型在不同图像条件下生成脸部的3D图像。