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. 发明授权

US08064653B2 Method and system of person identification by facial image 有权
标题翻译：人脸识别方法及系统
公开(公告)号：US08064653B2
公开(公告)日：2011-11-22
申请号：US11947588
申请日：2007-11-29
申请人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlezinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
发明人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlezinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
IPC分类号： G06K9/00 , G06K9/36
CPC分类号： G06K9/6202 , G06K9/00208 , G06K9/00248 , G06K9/00288
摘要： A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.
摘要翻译：描述识别面部图像的方法。使用眼睛瞳孔中心检测的方法，通过缩放和旋转角度对输入面部图像进行归一化。输入面部图像通过照明强度进一步归一化。通过处理从不同脸部位置拍摄的某些图像，或者通过基于立体对图像的3D脸部模型的初步重建获得模板图像。使用3D模型模板，以不同的旋转角度生成面部图像。输入面部图像和模板图像之间的距离由离散余弦变换（DCT）特征计算，由这些图像的重叠块定义。基于这些距离识别面部图像。

2. 发明申请

US20090141947A1 METHOD AND SYSTEM OF PERSON IDENTIFICATION BY FACIAL IMAGE 有权
标题翻译：人脸识别方法与系统
公开(公告)号：US20090141947A1
公开(公告)日：2009-06-04
申请号：US11947588
申请日：2007-11-29
申请人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlezinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
发明人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlezinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
IPC分类号： G06K9/00
CPC分类号： G06K9/6202 , G06K9/00208 , G06K9/00248 , G06K9/00288
摘要： A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.
摘要翻译：描述识别面部图像的方法。使用眼睛瞳孔中心检测的方法，通过缩放和旋转角度对输入面部图像进行归一化。输入面部图像通过照明强度进一步归一化。通过处理从不同脸部位置拍摄的某些图像，或者通过基于立体对图像的3D脸部模型的初步重建获得模板图像。使用3D模型模板，以不同的旋转角度生成面部图像。输入面部图像和模板图像之间的距离由离散余弦变换（DCT）特征计算，由这些图像的重叠块定义。基于这些距离识别面部图像。

3. 发明授权

US08184914B2 Method and system of person identification by facial image 有权
标题翻译：人脸识别方法及系统
公开(公告)号：US08184914B2
公开(公告)日：2012-05-22
申请号：US13270155
申请日：2011-10-10
申请人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
发明人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
IPC分类号： G06K9/68 , G06K9/00 , G06K9/62
CPC分类号： G06K9/6202 , G06K9/00208 , G06K9/00248 , G06K9/00288
摘要： A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.
摘要翻译：描述识别面部图像的方法。使用眼睛瞳孔中心检测的方法，通过缩放和旋转角度对输入面部图像进行归一化。输入面部图像通过照明强度进一步归一化。通过处理从不同脸部位置拍摄的某些图像，或者通过基于立体对图像的3D脸部模型的初步重建获得模板图像。使用3D模型模板，以不同的旋转角度生成面部图像。输入面部图像和模板图像之间的距离由离散余弦变换（DCT）特征计算，由这些图像的重叠块定义。基于这些距离识别面部图像。

4. 发明申请

US20130170759A1 Method and System of Person Identification by Facial Image 审中-公开
标题翻译：人脸识别方法与系统
公开(公告)号：US20130170759A1
公开(公告)日：2013-07-04
申请号：US13460733
申请日：2012-04-30
申请人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
发明人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
IPC分类号： G06K9/62
CPC分类号： G06K9/6202 , G06K9/00208 , G06K9/00248 , G06K9/00288
摘要： A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.
摘要翻译：描述识别面部图像的方法。使用眼睛瞳孔中心检测的方法，通过缩放和旋转角度对输入面部图像进行归一化。输入面部图像通过照明强度进一步归一化。通过处理从不同脸部位置拍摄的某些图像，或者通过基于立体对图像的3D脸部模型的初步重建获得模板图像。使用3D模型模板，以不同的旋转角度生成面部图像。输入面部图像和模板图像之间的距离由离散余弦变换（DCT）特征计算，由这些图像的重叠块定义。基于这些距离识别面部图像。

5. 发明申请

US20120027270A1 Method and System of Person Identification by Facial Image 有权
标题翻译：人脸识别方法与系统
公开(公告)号：US20120027270A1
公开(公告)日：2012-02-02
申请号：US13270155
申请日：2011-10-10
申请人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
发明人： Volodymyr Kyyko , Vyacheslav Matsello , Andriy Tsariov , Yuriy Musatenko , Mykhailo Schlesinger , Kostiantyn Kyiko , Oleksii Nedashkivskyi
IPC分类号： G06K9/00
CPC分类号： G06K9/6202 , G06K9/00208 , G06K9/00248 , G06K9/00288
摘要： A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.
摘要翻译：描述识别面部图像的方法。使用眼睛瞳孔中心检测的方法，通过缩放和旋转角度对输入面部图像进行归一化。输入面部图像通过照明强度进一步归一化。通过处理从不同脸部位置拍摄的某些图像，或者通过基于立体对图像的3D脸部模型的初步重建获得模板图像。使用3D模型模板，以不同的旋转角度生成面部图像。输入面部图像和模板图像之间的距离由离散余弦变换（DCT）特征计算，由这些图像的重叠块定义。基于这些距离识别面部图像。

6. 发明申请

US20090116695A1 SYSTEM AND METHOD FOR PROCESSING DIGITAL MEDIA 有权
标题翻译：用于处理数字媒体的系统和方法
公开(公告)号：US20090116695A1
公开(公告)日：2009-05-07
申请号：US11949128
申请日：2007-12-03
申请人： Yegor Anchyshkin , Yuriy Musatenko , Kostyantyn Milshteyn , Volodymyr Kyyko , Ivan Kovtun , Vyacheslav Matsello , Mykhailo Schlezinger
发明人： Yegor Anchyshkin , Yuriy Musatenko , Kostyantyn Milshteyn , Volodymyr Kyyko , Ivan Kovtun , Vyacheslav Matsello , Mykhailo Schlezinger
IPC分类号： G06K9/00
CPC分类号： G06K9/3266 , G06K9/00221 , G06K9/00711
摘要： A method for processing digital media is described. In one example embodiment, the method may include detecting an unknown object in a video frame, receiving inputs representing probable identities of the unknown object in the video frame from various sources, and associating each input with the unknown object detected in the video frame. The received inputs may be processed, compared with reference data and, based on the comparison, probable identities of the object associated with the input derived. The method may further include retrieving a likelihood of the input to match the unknown object from historical data and producing weights corresponding to the inputs, fusing the inputs and the relative weight associated with each input, and identifying the unknown object based on a comparison of the weighted distances from the unknown identify to a reference identity. The relative weights are chosen from the historical data to maximize correct recognition rate based on the history of recognitions and manual verification results.
摘要翻译：描述了处理数字媒体的方法。在一个示例实施例中，该方法可以包括检测视频帧中的未知对象，从各种来源接收表示视频帧中未知对象的可能身份的输入，并且将每个输入与在视频帧中检测到的未知对象相关联。可以处理接收的输入，与参考数据相比较，并且基于比较，与所输入的导出相关联的对象的可能的身份。该方法还可以包括从历史数据中检索输入的匹配未知对象的可能性，并产生与输入相对应的加权，将输入和与每个输入相关联的相对权重融合在一起，并且基于从未知身份到参考身份的加权距离。从历史数据中选择相对权重，以根据识别历史和手动验证结果最大化正确的识别率。

7. 发明授权

US08064641B2 System and method for identifying objects in video 有权
标题翻译：用于识别视频中对象的系统和方法
公开(公告)号：US08064641B2
公开(公告)日：2011-11-22
申请号：US11949128
申请日：2007-12-03
申请人： Yegor Anchyshkin , Yuriy Musatenko , Kostyantyn Milshteyn , Volodymyr Kyyko , Ivan Kovtun , Vyacheslav Matsello , Mykhailo Schlesinger
发明人： Yegor Anchyshkin , Yuriy Musatenko , Kostyantyn Milshteyn , Volodymyr Kyyko , Ivan Kovtun , Vyacheslav Matsello , Mykhailo Schlesinger
IPC分类号： G06K9/00
CPC分类号： G06K9/3266 , G06K9/00221 , G06K9/00711
摘要： A method for processing digital media is described. In one example embodiment, the method may include detecting an unknown object in a video frame, receiving inputs representing probable identities of the unknown object in the video frame from various sources, and associating each input with the unknown object detected in the video frame. The received inputs may be processed, compared with reference data and, based on the comparison, probable identities of the object associated with the input derived. The method may further include retrieving a likelihood of the input to match the unknown object from historical data and producing weights corresponding to the inputs, fusing the inputs and the relative weight associated with each input, and identifying the unknown object based on a comparison of the weighted distances from the unknown identify to a reference identity. The relative weights are chosen from the historical data to maximize correct recognition rate based on the history of recognitions and manual verification results.
摘要翻译：描述了处理数字媒体的方法。在一个示例实施例中，该方法可以包括检测视频帧中的未知对象，从各种来源接收表示视频帧中未知对象的可能身份的输入，并且将每个输入与在视频帧中检测到的未知对象相关联。可以处理接收的输入，与参考数据相比较，并且基于比较，与所输入的导出相关联的对象的可能的身份。该方法还可以包括从历史数据中检索输入的匹配未知对象的可能性，并产生与输入相对应的加权，将输入和与每个输入相关联的相对权重融合在一起，并且基于从未知身份到参考身份的加权距离。从历史数据中选择相对权重，以根据识别历史和手动验证结果最大化正确的识别率。

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