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

US08068645B2 Apparatus, method, and program for image processing 有权
标题翻译：用于图像处理的装置，方法和程序
公开(公告)号：US08068645B2
公开(公告)日：2011-11-29
申请号：US11434200
申请日：2006-05-16
申请人： Hirokazu Kameyama , Akira Yoda , Wataru Ito
发明人： Hirokazu Kameyama , Akira Yoda , Wataru Ito
IPC分类号： G06K9/00
CPC分类号： G06T11/60
摘要： In order to cause a structure such as a human face in an image to become unidentifiable while causing the image to have a natural finish, a parameter acquisition unit obtains weighting parameters representing a characteristic of an individual in a face region in the image by fitting to the face region detected by a face detection unit a mathematical model generated by a method of AAM using a plurality of sample images representing human faces. A reconstruction unit changes the weighting parameters to become smaller, and reconstructs the face region by using the parameters having been changed.
摘要翻译：为了使诸如图像中的人脸等结构在使图像具有自然光洁度的同时变得无法识别，参数获取单元通过拟合到图像的脸部区域中来获得表示个人的特征的加权参数由脸部检测单元检测的面部区域是使用表示人脸的多个样本图像的由AAM的方法生成的数学模型。重建单元将加权参数改变为更小，并且通过使用已经改变的参数来重构面部区域。

2. 发明申请

US20060257041A1 Apparatus, method, and program for image processing 有权
标题翻译：用于图像处理的装置，方法和程序
公开(公告)号：US20060257041A1
公开(公告)日：2006-11-16
申请号：US11434200
申请日：2006-05-16
申请人： Hirokazu Kameyama , Akira Yoda , Wataru Ito
发明人： Hirokazu Kameyama , Akira Yoda , Wataru Ito
IPC分类号： G06K9/40 , G06K9/00
CPC分类号： G06T11/60
摘要： In order to cause a structure such as a human face in an image to become unidentifiable while causing the image to have a natural finish, a parameter acquisition unit obtains weighting parameters representing a characteristic of an individual in a face region in the image by fitting to the face region detected by a face detection unit a mathematical model generated by a method of AAM using a plurality of sample images representing human faces. A reconstruction unit changes the weighting parameters to become smaller, and reconstructs the face region by using the parameters having been changed.
摘要翻译：为了使诸如图像中的人脸等结构在使图像具有自然光洁度的同时变得无法识别，参数获取单元通过拟合到图像的脸部区域中来获得表示个人的特征的加权参数由脸部检测单元检测的面部区域是使用表示人脸的多个样本图像的由AAM的方法生成的数学模型。重建单元将加权参数改变为更小，并且通过使用已经改变的参数来重构面部区域。

3. 发明授权

US08078010B2 Method and device for video image processing, calculating the similarity between video frames, and acquiring a synthesized frame by synthesizing a plurality of contiguous sampled frames 有权
标题翻译：用于视频图像处理的方法和装置，计算视频帧之间的相似度，以及通过合成多个连续采样帧来获取合成帧
公开(公告)号：US08078010B2
公开(公告)日：2011-12-13
申请号：US12754718
申请日：2010-04-06
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/32
CPC分类号： G06T3/4053 , G06T7/32 , H04N5/145
摘要： To acquire a high-resolution frame from a plurality of frames sampled from a video image, it is necessary to obtain a high-resolution frame with reduced picture quality degradation regardless of motion of a subject included in the frame. Because of this, between a plurality of contiguous frames FrN and FrN+1, there is estimated a correspondent relationship. Based on the correspondent relationship, the frames FrN+1 and FrN are interposed to obtain first and second interpolated frames FrH1 and FrH2. Based on the correspondent relationship, the coordinates of the frame FrN+1 are transformed, and from a correlation value with the frame FrN, there is obtained a weighting coefficient α(x°, y°) that makes the weight of the first interpolated frame FrH1 greater as a correlation becomes greater. With the weighting coefficient, the first and second interpolated frames are weighted and added to acquire a synthesized frame FrG.
摘要翻译：为了从从视频图像采样的多个帧获取高分辨率帧，需要获得具有降低的图像质量劣化的高分辨率帧，而不管帧中包括的对象的运动如何。因此，在多个相邻帧FrN和FrN + 1之间，估计出对应关系。基于对应关系，插入帧FrN + 1和FrN以获得第一和第二内插帧FrH1和FrH2。基于对应关系，对帧FrN + 1的坐标进行变换，并且从与帧FrN的相关值获得加权系数α（x°，y°），其使得第一内插帧的权重相关性较高的FrH1变大。利用加权系数，对第一和第二内插帧进行加权和相加以获得合成帧FrG。

4. 发明授权

US07729563B2 Method and device for video image processing, calculating the similarity between video frames, and acquiring a synthesized frame by synthesizing a plurality of contiguous sampled frames 失效
标题翻译：用于视频图像处理的方法和装置，计算视频帧之间的相似度，以及通过合成多个连续采样帧来获取合成帧
公开(公告)号：US07729563B2
公开(公告)日：2010-06-01
申请号：US10646753
申请日：2003-08-25
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/32
CPC分类号： G06T3/4053 , G06T7/32 , H04N5/145
摘要： To acquire a high-resolution frame from a plurality of frames sampled from a video image, it is necessary to obtain a high-resolution frame with reduced picture quality degradation regardless of motion of a subject included in the frame. Because of this, between a plurality of contiguous frames FrN and FrN+1, there is estimated a correspondent relationship. Based on the correspondent relationship, the frames FrN+1 and FrN are interposed to obtain first and second interpolated frames FrH1 and FrH2. Based on the correspondent relationship, the coordinates of the frame FrN+1 are transformed, and from a correlation value with the frame FrN, there is obtained a weighting coefficient α(x°, y°) that makes the weight of the first interpolated frame FrH1 greater as a correlation becomes greater. With the weighting coefficient, the first and second interpolated frames are weighted and added to acquire a synthesized frame FrG.
摘要翻译：为了从从视频图像采样的多个帧获取高分辨率帧，需要获得具有降低的图像质量劣化的高分辨率帧，而不管帧中包括的对象的运动如何。因此，在多个相邻帧FrN和FrN + 1之间，估计出对应关系。基于对应关系，插入帧FrN + 1和FrN以获得第一和第二内插帧FrH1和FrH2。基于对应关系，对帧FrN + 1的坐标进行变换，并且从与帧FrN的相关值获得加权系数α（x°，y°），其使得第一内插帧的权重相关性较高的FrH1变大。利用加权系数，对第一和第二内插帧进行加权和相加以获得合成帧FrG。

5. 发明授权

US08275219B2 Method and device for video image processing, calculating the similarity between video frames, and acquiring a synthesized frame by synthesizing a plurality of contiguous sampled frames 失效
标题翻译：用于视频图像处理的方法和装置，计算视频帧之间的相似度，以及通过合成多个连续采样帧来获取合成帧
公开(公告)号：US08275219B2
公开(公告)日：2012-09-25
申请号：US13172437
申请日：2011-06-29
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/32
CPC分类号： G06T3/4053 , G06T7/32 , H04N5/145
摘要： To acquire a high-resolution frame from a plurality of frames sampled from a video image, it is necessary to obtain a high-resolution frame with reduced picture quality degradation regardless of motion of a subject included in the frame. Because of this, between a plurality of contiguous frames FrN and FrN+1, there is estimated a correspondent relationship. Based on the correspondent relationship, the frames FrN+1 and FrN are interposed to obtain first and second interpolated frames FrH1 and FrH2. Based on the correspondent relationship, the coordinates of the frame FrN+1 are transformed, and from a correlation value with the frame FrN, there is obtained a weighting coefficient α (x′, y′) that makes the weight of the first interpolated frame FrH1 greater as a correlation becomes greater. With the weighting coefficient, the first and second interpolated frames are weighted and added to acquire a synthesized frame FrG.
摘要翻译：为了从从视频图像采样的多个帧获取高分辨率帧，需要获得具有降低的图像质量劣化的高分辨率帧，而不管帧中包括的对象的运动如何。因此，在多个相邻帧FrN和FrN + 1之间，估计出对应关系。基于对应关系，插入帧FrN + 1和FrN以获得第一和第二内插帧FrH1和FrH2。根据对应关系，对帧FrN + 1的坐标进行变换，从与帧FrN的相关值得到加权系数α（x'，y'），使加权系数α 相关性较高的FrH1变大。利用加权系数，对第一和第二内插帧进行加权和相加以获得合成帧FrG。

6. 发明授权

US07391931B2 Method, apparatus, and program for moving image synthesis 有权
标题翻译：用于运动图像合成的方法，装置和程序
公开(公告)号：US07391931B2
公开(公告)日：2008-06-24
申请号：US10750461
申请日：2004-01-02
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/32 , H04B1/66
CPC分类号： G06T3/4061
摘要： A single high resolution frame is obtained from a plurality of frames sampled from moving image data, regardless of movement of a subject included in the frames. Patches are provided in a plurality of frames including a reference frame and other frames. The patches are moved and/or deformed, and correspondent relationships are estimated for each frame. The other frames are coordinate converted based on the estimated correspondent relationships. Correlative values, which represent the degrees of correlation between the other frames and the reference frame, are calculated. The number of regions within the patches is changed, and the correlative values are calculated in the same manner. A synthesized frame is generated from the plurality of frames based on the correspondent relationship, which was estimated for the number of regions that yields the maximal correlation.
摘要翻译：从运动图像数据采样的多个帧中获得单个高分辨率帧，而不管帧中包括的对象的移动。补片设置在包括参考框架和其他框架的多个框架中。补片被移动和/或变形，并且针对每个帧估计对应关系。基于估计的对应关系，其他帧被协调转换。计算表示其他帧与参考帧之间的相关程度的相关值。改变贴片内的区域数量，并以相同的方式计算相关值。基于对产生最大相关性的区域的数量估计的对应关系，从多个帧生成合成帧。

7. 发明申请

US20070014483A1 Apparatus, method and program for image processing 审中-公开
标题翻译：用于图像处理的装置，方法和程序
公开(公告)号：US20070014483A1
公开(公告)日：2007-01-18
申请号：US11514886
申请日：2006-09-05
申请人： Yoshiya Ohara , Hirokazu Kameyama , Yuanzhong Li , Wataru Ito
发明人： Yoshiya Ohara , Hirokazu Kameyama , Yuanzhong Li , Wataru Ito
IPC分类号： G06K9/40 , G06K9/00
CPC分类号： G06K9/00241
摘要： For enabling a change in lighting pattern in an image, adjustment of a shadow pattern is aimed at in an image. For this purpose, a parameter acquisition unit obtains weighting parameters representing the shadow pattern in a face region in the image by fitting to the face region detected by a face detection unit a mathematical model generated by a method of AAM using a plurality of sample images representing human faces in different lighting conditions. A shadow pattern adjustment unit adjusts the shadow pattern in the face region based on the weighting parameters having been obtained.
摘要翻译：为了能够改变图像中的照明图案，在图像中针对阴影图案的调整。为此，参数获取单元通过拟合由面部检测单元检测到的面部区域获得表示图像中的脸部区域中的阴影图案的加权参数，该数学模型通过使用多个样本图像代表AAM的方法生成的数学模型人脸在不同的照明条件下。阴影图案调整单元基于已经获得的加权参数来调整面部区域中的阴影图案。

8. 发明授权

US08805121B2 Method and device for video image processing, calculating the similarity between video frames, and acquiring a synthesized frame by synthesizing a plurality of contiguous sampled frames 有权
标题翻译：用于视频图像处理的方法和装置，计算视频帧之间的相似度，以及通过合成多个连续采样帧来获取合成帧
公开(公告)号：US08805121B2
公开(公告)日：2014-08-12
申请号：US13593636
申请日：2012-08-24
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/32
CPC分类号： G06T3/4053 , G06T7/32 , H04N5/145
摘要： To acquire a high-resolution frame from a plurality of frames sampled from a video image, it is necessary to obtain a high-resolution frame with reduced picture quality degradation regardless of motion of a subject included in the frame. Because of this, between a plurality of contiguous frames FrN and FrN+1, there is estimated a correspondent relationship. Based on the correspondent relationship, the frames FrN+1 and FrN are interposed to obtain first and second interpolated frames FrH1 and FrH2. Based on the correspondent relationship, the coordinates of the frame FrN+1 are transformed, and from a correlation value with the frame FrN, there is obtained a weighting coefficient α(x°, y°) that makes the weight of the first interpolated frame FrH1 greater as a correlation becomes greater. With the weighting coefficient, the first and second interpolated frames are weighted and added to acquire a synthesized frame FrG.
摘要翻译：为了从从视频图像采样的多个帧获取高分辨率帧，需要获得具有降低的图像质量劣化的高分辨率帧，而不管帧中包括的对象的运动如何。因此，在多个相邻帧FrN和FrN + 1之间，估计出对应关系。基于对应关系，插入帧FrN + 1和FrN以获得第一和第二内插帧FrH1和FrH2。基于对应关系，对帧FrN + 1的坐标进行变换，并且从与帧FrN的相关值获得加权系数α（x°，y°），其使得第一内插帧的权重相关性较高的FrH1变大。利用加权系数，对第一和第二内插帧进行加权和相加以获得合成帧FrG。

9. 发明申请

US20060257047A1 Image processing apparatus, image processing method, and image processing program 有权
标题翻译：图像处理装置，图像处理方法和图像处理程序
公开(公告)号：US20060257047A1
公开(公告)日：2006-11-16
申请号：US11431599
申请日：2006-05-11
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/40 , G06K9/46
CPC分类号： G06K9/00248 , G06K9/40 , G06K9/621
摘要： In order to accurately remove an unnecessary periodic noise component from an image, a reconstruction unit generates a reconstructed image without a periodic noise component by fitting to a face region detected in an image by a face detection unit a mathematical model generated according a method of AAM using a plurality of sample images representing human faces without a periodic noise component. The periodic noise component is extracted by a difference between the face region and the reconstructed image, and a frequency of the noise component is determined. The noise component of the determined frequency is then removed from the image.
摘要翻译：为了从图像中精确地去除不必要的周期性噪声分量，重建单元通过适合面部检测单元在图像中检测到的面部区域产生无周期噪声分量的重建图像，该数学模型根据AAM的方法生成使用表示人脸的多个样本图像而没有周期性噪声分量。通过面部区域和重建图像之间的差异提取周期性噪声分量，并且确定噪声分量的频率。然后从图像中去除所确定的频率的噪声分量。

10. 发明授权

US08107764B2 Image processing apparatus, image processing method, and image processing program 有权
标题翻译：图像处理装置，图像处理方法和图像处理程序
公开(公告)号：US08107764B2
公开(公告)日：2012-01-31
申请号：US11431599
申请日：2006-05-11
申请人： Hirokazu Kameyama , Wataru Ito
发明人： Hirokazu Kameyama , Wataru Ito
IPC分类号： G06K9/40
CPC分类号： G06K9/00248 , G06K9/40 , G06K9/621
摘要： In order to accurately remove an unnecessary periodic noise component from an image, a reconstruction unit generates a reconstructed image without a periodic noise component by fitting to a face region detected in an image by a face detection unit a mathematical model generated according a method of AAM using a plurality of sample images representing human faces without a periodic noise component. The periodic noise component is extracted by a difference between the face region and the reconstructed image, and a frequency of the noise component is determined. The noise component of the determined frequency is then removed from the image.
摘要翻译：为了从图像中精确地去除不必要的周期性噪声分量，重建单元通过适合面部检测单元在图像中检测到的面部区域产生无周期噪声分量的重建图像，该数学模型根据AAM的方法生成使用表示人脸的多个样本图像而没有周期性噪声分量。通过面部区域和重建图像之间的差异提取周期性噪声分量，并且确定噪声分量的频率。然后从图像中去除所确定的频率的噪声分量。

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