公开(公告)号：US08055029B2

公开(公告)日：2011-11-08

申请号：US12063089

申请日：2007-06-18

申请人： Stefan Petrescu ,  Peter Corcoran ,  Eran Steinberg ,  Petronel Bigioi ,  Alexandru Drimbarean

发明人： Stefan Petrescu ,  Peter Corcoran ,  Eran Steinberg ,  Petronel Bigioi ,  Alexandru Drimbarean

IPC分类号： G06K9/62

CPC分类号： G06K9/00 ,  G06K9/00234 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/62 ,  G06K9/6257 ,  G06K9/6857 ,  H04N1/2112 ,  H04N1/32112 ,  H04N1/32128 ,  H04N5/232 ,  H04N5/23219 ,  H04N2101/00 ,  H04N2201/0084 ,  H04N2201/3205

摘要： An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

摘要翻译： 用于跟踪图像流中的面部的图像处理装置从包括一个或多个面部区域的图像流中迭代地接收获取的图像。 所获取的图像以指定的分辨率被子采样以提供次采样图像。 然后对子采样图像的至少一部分计算整体图像。 将固定大小的脸部检测应用于积分图像的至少一部分以提供一组候选面部区域。 响应于所生成的候选面部区域的集合和任何先前检测到的候选面部区域，调整分辨率以对后续获取的图像进行子采样。

公开(公告)号：US08320641B2

公开(公告)日：2012-11-27

申请号：US12142134

申请日：2008-06-19

申请人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

发明人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G06K9/0061 ,  G06T5/008 ,  G06T5/50 ,  G06T7/90 ,  G06T7/97 ,  G06T2207/20008 ,  G06T2207/30201 ,  G06T2207/30216

摘要： A method for red-eye detection in an acquired digital image acquiring one or more preview or other reference images without a flash. Any red regions that exist within the one or more reference images are determined. A main image is acquired with a flash of approximately a same scene as the one or more reference images. The main image is analyzed to determine any candidate red eye defect regions that exist within the main image. Any red regions determined to exist within the one or more reference images are compared with any candidate red eye defect regions determined to exist within the main image. Any candidate red eye defect regions within the main image corresponding to red regions determined also to exist within the one or more reference images are removed as candidate red eye defect regions.

摘要翻译： 一种获取的数字图像中的红眼检测方法，用于在不闪光的情况下获取一个或多个预览或其他参考图像。 确定存在于一个或多个参考图像内的任何红色区域。 以与一个或多个参考图像大致相同的场景的闪光获取主图像。 分析主图像以确定存在于主图像内的任何候选红眼缺陷区域。 将确定存在于一个或多个参考图像内的任何红色区域与确定存在于主图像内的任何候选红眼缺陷区域进行比较。 除了确定还存在于一个或多个参考图像内的对应于红色区域的主图像内的候选红眼缺陷区域作为候选红眼缺陷区域被去除。

公开(公告)号：US20120069198A1

公开(公告)日：2012-03-22

申请号：US13190863

申请日：2011-07-26

申请人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran ,  Mihai Ciuc ,  Adrian Capata

发明人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran ,  Mihai Ciuc ,  Adrian Capata

IPC分类号： H04N5/262 ,  H04N5/225

CPC分类号： H04N5/262 ,  G06K9/00228 ,  G06K9/036 ,  G06K9/3208 ,  G06T7/11 ,  G06T2207/30196 ,  H04N5/222 ,  H04N5/2226 ,  H04N5/23219

摘要： A technique involves distinguishing between foreground and background regions of a digital image of a scene. First and second images are captured of nominally a same scene. The first image is a relatively high resolution image taken with the foreground more in focus than the background, while the second image is a relatively low resolution reference image taken with the background more in focus than the foreground. Regions of the captured images are assigned as foreground or background. In accordance with the assigning, one or more processed images are rendered based on the first image or the second image, or both.

摘要翻译： 一种技术涉及区分场景的数字图像的前景和背景区域。 第一和第二个图像被捕获在名义上相同的场景中。 第一个图像是一个相对较高的分辨率图像，前景比背景更聚焦，而第二个图像是一个相对较低的分辨率参考图像，背景比前景更为集中。 拍摄图像的区域被分配为前景或背景。 根据分配，基于第一图像或第二图像或两者来呈现一个或多个经处理的图像。

公开(公告)号：US20110221936A1

公开(公告)日：2011-09-15

申请号：US13113648

申请日：2011-05-23

申请人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

发明人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

IPC分类号： H04N5/217 ,  G06K9/00

CPC分类号： G06K9/00 ,  G06K9/0061 ,  G06T5/008 ,  G06T5/50 ,  G06T7/90 ,  G06T7/97 ,  G06T2207/20008 ,  G06T2207/30201 ,  G06T2207/30216

摘要： A method for red-eye detection in an acquired digital image acquiring one or more preview or other reference images without a flash. Any red regions that exist within the one or more reference images are determined. A main image is acquired with a flash of approximately a same scene as the one or more reference images. The main image is analyzed to determine any candidate red eye defect regions that exist within the main image. Any red regions determined to exist within the one or more reference images are compared with any candidate red eye defect regions determined to exist within the main image. Any candidate red eye defect regions within the main image corresponding to red regions determined also to exist within the one or more reference images are removed as candidate red eye defect regions.

摘要翻译： 一种获取的数字图像中的红眼检测方法，用于在不闪光的情况下获取一个或多个预览或其他参考图像。 确定存在于一个或多个参考图像内的任何红色区域。 以与一个或多个参考图像大致相同的场景的闪光获取主图像。 分析主图像以确定存在于主图像内的任何候选红眼缺陷区域。 将确定存在于一个或多个参考图像内的任何红色区域与确定存在于主图像内的任何候选红眼缺陷区域进行比较。 除了确定还存在于一个或多个参考图像内的对应于红色区域的主图像内的候选红眼缺陷区域作为候选红眼缺陷区域被去除。

公开(公告)号：US08213737B2

公开(公告)日：2012-07-03

申请号：US12142773

申请日：2008-06-20

申请人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran

发明人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran

IPC分类号： G06K9/40

CPC分类号： G06K9/40 ,  G06K9/00248 ,  G06K9/0061 ,  G06K9/3208 ,  G06K9/4652 ,  G06K9/48 ,  G06T3/4038 ,  G06T5/003 ,  G06T11/60 ,  G06T2207/10004 ,  G06T2207/20201 ,  G06T2207/20221 ,  G06T2207/30168 ,  G06T2207/30216 ,  H04N5/2258 ,  H04N5/23219 ,  H04N5/23222 ,  H04N5/2354 ,  H04N5/272 ,  H04N5/345 ,  H04N5/347 ,  H04N5/772 ,  H04N5/907 ,  H04N9/8042

摘要： A digital image processing technique detects and corrects visual imperfections using a reference image. A main image and one or more reference images having a temporal and/or spatial overlap and/or proximity with the original image are captured. Device information, image data and/or meta data are analyzed of the one or more reference images relating to a defect in the main image. The device corrects the defect based on the information, image data and/or meta-data to create an enhanced version of the main image.

摘要翻译： 数字图像处理技术使用参考图像检测和校正视觉缺陷。 捕获具有与原始图像的时间和/或空间重叠和/或邻近的主图像和一个或多个参考图像。 分析与主图像中的缺陷相关的一个或多个参考图像的装置信息，图像数据和/或元数据。 该设备基于信息，图像数据和/或元数据来校正缺陷以创建主图像的增强版本。

公开(公告)号：US08135184B2

公开(公告)日：2012-03-13

申请号：US13113648

申请日：2011-05-23

申请人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

发明人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G06K9/0061 ,  G06T5/008 ,  G06T5/50 ,  G06T7/90 ,  G06T7/97 ,  G06T2207/20008 ,  G06T2207/30201 ,  G06T2207/30216

摘要： A method for red-eye detection in an acquired digital image acquiring one or more preview or other reference images without a flash. Any red regions that exist within the one or more reference images are determined. A main image is acquired with a flash of approximately a same scene as the one or more reference images. The main image is analyzed to determine any candidate red eye defect regions that exist within the main image. Any red regions determined to exist within the one or more reference images are compared with any candidate red eye defect regions determined to exist within the main image. Any candidate red eye defect regions within the main image corresponding to red regions determined also to exist within the one or more reference images are removed as candidate red eye defect regions.

摘要翻译： 一种获取的数字图像中的红眼检测方法，用于在不闪光的情况下获取一个或多个预览或其他参考图像。 确定存在于一个或多个参考图像内的任何红色区域。 以与一个或多个参考图像大致相同的场景的闪光获取主图像。 分析主图像以确定存在于主图像内的任何候选红眼缺陷区域。 将确定存在于一个或多个参考图像内的任何红色区域与确定存在于主图像内的任何候选红眼缺陷区域进行比较。 除了确定还存在于一个或多个参考图像内的对应于红色区域的主图像内的候选红眼缺陷区域作为候选红眼缺陷区域被去除。

公开(公告)号：US07953251B1

公开(公告)日：2011-05-31

申请号：US12947731

申请日：2010-11-16

申请人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

发明人： Eran Steinberg ,  Peter Corcoran ,  Yury Prilutsky ,  Petronel Bigioi ,  Adrian Zamfir ,  Florin Nanu ,  Alexandru Drimbarean

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G06K9/0061 ,  G06T5/008 ,  G06T5/50 ,  G06T7/90 ,  G06T7/97 ,  G06T2207/20008 ,  G06T2207/30201 ,  G06T2207/30216

摘要： A method for red-eye detection in an acquired digital image acquiring one or more preview or other reference images without a flash. Any red regions that exist within the one or more reference images are determined. A main image is acquired with a flash of approximately a same scene as the one or more reference images. The main image is analyzed to determine any candidate red eye defect regions that exist within the main image. Any red regions determined to exist within the one or more reference images are compared with any candidate red eye defect regions determined to exist within the main image. Any candidate red eye defect regions within the main image corresponding to red regions determined also to exist within the one or more reference images are removed as candidate red eye defect regions.

摘要翻译： 一种获取的数字图像中的红眼检测方法，用于在不闪光的情况下获取一个或多个预览或其他参考图像。 确定存在于一个或多个参考图像内的任何红色区域。 以与一个或多个参考图像大致相同的场景的闪光获取主图像。 分析主图像以确定存在于主图像内的任何候选红眼缺陷区域。 将确定存在于一个或多个参考图像内的任何红色区域与确定存在于主图像内的任何候选红眼缺陷区域进行比较。 除了确定还存在于一个或多个参考图像内的对应于红色区域的主图像内的候选红眼缺陷区域作为候选红眼缺陷区域被去除。

公开(公告)号：US20080316328A1

公开(公告)日：2008-12-25

申请号：US12140827

申请日：2008-06-17

申请人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran ,  Mihai Ciuc ,  Adrian Capata

发明人： Eran Steinberg ,  Petronel Bigioi ,  Adrian Zamfir ,  Alexandru Drimbarean ,  Peter Corcoran ,  Mihai Ciuc ,  Adrian Capata

IPC分类号： H04N5/228 ,  G06K9/34 ,  G06K9/36

CPC分类号： H04N5/262 ,  G06K9/00228 ,  G06K9/036 ,  G06K9/3208 ,  G06T7/11 ,  G06T2207/30196 ,  H04N5/222 ,  H04N5/2226 ,  H04N5/23219

摘要： A technique involves distinguishing between foreground and background regions of a digital image of a scene. First and second images are captured of nominally a same scene. The first image is a relatively high resolution image taken with the foreground more in focus than the background, while the second image is a relatively low resolution reference image taken with the background more in focus than the foreground. Regions of the captured images are assigned as foreground or background. In accordance with the assigning, one or more processed images are rendered based on the first image or the second image, or both.

摘要翻译： 一种技术涉及区分场景的数字图像的前景和背景区域。 第一和第二个图像被捕获在名义上相同的场景中。 第一个图像是一个相对较高的分辨率图像，前景比背景更聚焦，而第二个图像是一个相对较低的分辨率参考图像，背景比前景更为集中。 拍摄图像的区域被分配为前景或背景。 根据分配，基于第一图像或第二图像或两者来呈现一个或多个经处理的图像。

公开(公告)号：US07315631B1

公开(公告)日：2008-01-01

申请号：US11464083

申请日：2006-08-11

申请人： Peter Corcoran ,  Eran Steinberg ,  Stefan Petrescu ,  Alexandru Drimbarean ,  Florin Nanu ,  Alexei Pososin ,  Petronel Biglol

发明人： Peter Corcoran ,  Eran Steinberg ,  Stefan Petrescu ,  Alexandru Drimbarean ,  Florin Nanu ,  Alexei Pososin ,  Petronel Biglol

IPC分类号： G06K9/00 ,  G06K9/32 ,  G06K9/36

CPC分类号： G06K9/00 ,  G06K9/00234 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/62 ,  G06K9/6257 ,  G06K9/6857 ,  H04N1/2112 ,  H04N1/32112 ,  H04N1/32128 ,  H04N5/232 ,  H04N5/23219 ,  H04N2101/00 ,  H04N2201/0084 ,  H04N2201/3205

摘要： An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream potentially including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

公开(公告)号：US20120070087A1

公开(公告)日：2012-03-22

申请号：US13245738

申请日：2011-09-26

申请人： Stefan Petrescu ,  Peter Corcoran ,  Eran Steinberg ,  Petronel Bigioi ,  Alexandru Drimbarean

发明人： Stefan Petrescu ,  Peter Corcoran ,  Eran Steinberg ,  Petronel Bigioi ,  Alexandru Drimbarean

IPC分类号： G06K9/46

CPC分类号： G06K9/00 ,  G06K9/00234 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06K9/62 ,  G06K9/6257 ,  G06K9/6857 ,  H04N1/2112 ,  H04N1/32112 ,  H04N1/32128 ,  H04N5/232 ,  H04N5/23219 ,  H04N2101/00 ,  H04N2201/0084 ,  H04N2201/3205

摘要： An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

摘要翻译： 用于跟踪图像流中的面部的图像处理装置从包括一个或多个面部区域的图像流中迭代地接收获取的图像。 所获取的图像以指定的分辨率被子采样以提供次采样图像。 然后对子采样图像的至少一部分计算整体图像。 将固定大小的脸部检测应用于积分图像的至少一部分以提供一组候选面部区域。 响应于所生成的候选面部区域的集合和任何先前检测到的候选面部区域，调整分辨率以对后续获取的图像进行子采样。