专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明申请

WO2009039876A1 FACE TRACKING IN A CAMERA PROCESSOR 审中-公开
标题翻译：相机处理器中的面部跟踪
公开(公告)号：WO2009039876A1
公开(公告)日：2009-04-02
申请号：PCT/EP2007/009763
申请日：2007-11-12
申请人： FOTONATION VISION LIMITED , CORCORAN, Peter , PETRESCU, Stefan, Mirel , GANGEA, Mihnea , BIGIOI, Petronel , POSOSIN, Alexei
发明人： CORCORAN, Peter , PETRESCU, Stefan, Mirel , GANGEA, Mihnea , BIGIOI, Petronel , POSOSIN, Alexei
IPC分类号： G06K9/68
CPC分类号： G06K9/00 , G06K9/00228 , G06K9/6857
摘要： A method operable in a digital image acquisition system having no photographic film is provided. The method comprises receiving a relatively low resolution image of a scene from an image stream, wherein the scene potentially includes one or more faces. At least one high quality face classifier is applied to the image to identify relatively large and medium sized face regions and at least one relaxed face classifier is applied to the image to identify relatively small sized face regions. A relatively high resolution image of nominally the same scene is received and at least one high quality face classifier is applied to the identified small sized face regions in the higher resolution version of said image.
摘要翻译：提供了一种在没有摄影胶片的数字图像采集系统中可操作的方法。该方法包括从图像流接收场景的相对较低分辨率的图像，其中该场景潜在地包括一个或多个面。至少一个高质量的脸部分类器被应用于图像以识别相对大的和中等大小的脸部区域，并且至少一个放松的面部分类器被应用于图像以识别相对小的脸部区域。接收名义上相同的场景的相对高分辨率的图像，并且至少一个高质量的面部分类器被应用于所述图像的较高分辨率版本中的所识别的小尺寸的脸部区域。

62. 发明申请

WO2008151802A1 FAST MOTION ESTIMATION METHOD 审中-公开
标题翻译：快速运动估计方法
公开(公告)号：WO2008151802A1
公开(公告)日：2008-12-18
申请号：PCT/EP2008/004729
申请日：2008-06-12
申请人： FOTONATION IRELAND LIMITED , ALBU, Felix , FLOREA, Corneliu , ZAMFIR, Adrian , DRIMBAREAN, Alexandru , CORCORAN, Peter
发明人： ALBU, Felix , FLOREA, Corneliu , ZAMFIR, Adrian , DRIMBAREAN, Alexandru , CORCORAN, Peter
IPC分类号： H04N5/14 , H04N5/232
CPC分类号： H04N5/144 , H04N5/23248 , H04N5/23261 , H04N19/527
摘要： An estimated total camera motion between temporally proximate image frames is computed. A desired component of the estimated total camera motion is determined including distinguishing an undesired component of the estimated total camera motion, and including characterizing vector values of motion between the image frames. A counter is incremented for each pixel group having a summed luminance that is greater than a threshold. A counter may be decremented for pixels that are under a second threshold, or a zero bit may be applied to pixels below a single threshold. The threshold or thresholds is/are determined based on a dynamic luminance range of the sequence. The desired camera motion is computed including representing the vector values based on final values of counts for the image frames. A corrected image sequence is generated including the desired component of the estimated total camera motion, and excluding the undesired component.
摘要翻译：计算时间上接近的图像帧之间的估计的总相机运动。确定所估计的总相机运动的期望分量，包括区分估计的全部相机运动的不期望分量，并且包括图像帧之间的运动的特征向量值。对于具有大于阈值的总和亮度的每个像素组，计数器递增。对于处于第二阈值以下的像素，计数器可以递减，或者可将零位施加到单个阈值以下的像素。基于序列的动态亮度范围来确定阈值或阈值。计算所需的相机运动，包括基于图像帧的计数的最终值来表示矢量值。产生校正的图像序列，其包括所估计的全部相机运动的期望分量，并且排除不期望的分量。

63. 发明申请

WO2008131438A2 DETECTION AND ESTIMATION OF CAMERA MOVEMENT 审中-公开
标题翻译：相机运动的检测和估计
公开(公告)号：WO2008131438A2
公开(公告)日：2008-10-30
申请号：PCT/US2008/061328
申请日：2008-04-23
申请人： FOTONATION IRELAND LIMITED , DRIMBAREAN, Alexandru , ZAMFIR, Adrian , FLOREA, Corneliu , ALBU, Felix , MISS, Dan , STEINBERG, Eran , CORCORAN, Peter , PRILUTSKY, Yury
发明人： DRIMBAREAN, Alexandru , ZAMFIR, Adrian , FLOREA, Corneliu , ALBU, Felix , MISS, Dan , STEINBERG, Eran , CORCORAN, Peter , PRILUTSKY, Yury
IPC分类号： G06K9/74
CPC分类号： H04N5/23267 , G03B7/08 , G06T5/003 , G06T7/20 , G06T2207/20201 , H04N5/145 , H04N5/23248 , H04N5/23258
摘要： A digital camera includes an optical system, a main image sensor and a camera motion sensor for estimating relative camera-object motion during image capture. A processor estimates camera motion based on information obtained by the camera motion photo-sensor while the camera is exposed to an image of a scene. The processor reduces or removes a motion blur effect from the main image permitting a processed version of the main image to be thereafter rendered.
摘要翻译：数字照相机包括光学系统，主图像传感器和照相机运动传感器，用于在图像拍摄期间估计相对摄像机物体运动。当相机曝光到场景的图像时，处理器基于由相机运动光电传感器获得的信息来估计相机运动。处理器从主图像减少或去除允许主图像的处理版本之后的运动模糊效果。

64. 发明申请

WO2008104549A3 SEPARATING DIRECTIONAL LIGHTING VARIABILITY IN STATISTICAL FACE MODELLING BASED ON TEXTURE SPACE DECOMPOSITION 审中-公开
标题翻译：基于纹理空间分解的统计人脸建模中的方向照明可变性
公开(公告)号：WO2008104549A3
公开(公告)日：2008-10-30
申请号：PCT/EP2008052329
申请日：2008-02-26
申请人： FOTONATION VISION LTD , IONITA MIRCEA , BACIVAROV IOANA , CORCORAN PETER
发明人： IONITA MIRCEA , BACIVAROV IOANA , CORCORAN PETER
IPC分类号： G06K9/00 , G06K9/46 , G06K9/64
CPC分类号： G06K9/40 , G06K9/00 , G06K9/00268 , G06K9/00281 , G06K9/4661 , G06K9/621 , G06T5/007 , H04N5/2351 , H04N5/2354
摘要： A technique for determining a characteristic of a face or certain other object within a scene captured in a digital image including acquiring an image and applying a linear texture model that is constructed based on a training data set and that includes a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations. A fit of the model to the face or certain other object is obtained including adjusting one or more individual values of one or more of the model components of the linear texture model. Based on the obtained fit of the model to the face or certain other object in the scene, a characteristic of the face or certain other object is determined.
摘要翻译：一种用于确定在数字图像中捕捉的场景内的面部或某个其它对象的特性的技术，包括：获取图像并应用基于训练数据集构建的并且包括一类对象的线性纹理模型，所述对象包括第一表现出对定向照明变化的依赖性的模型组件的子集以及与定向照明变化无关的模型组件的第二子集。获得模型与脸部或某个其他物体的拟合，包括调整线性纹理模型的一个或多个模型分量的一个或多个单独值。基于所获得的模型对场景中的脸部或某个其他物体的拟合，确定脸部或某个其他物体的特征。

65. 发明申请

WO2008107002A1 FACE SEARCHING AND DETECTION IN A DIGITAL IMAGE ACQUISITION DEVICE 审中-公开
标题翻译：数字图像获取装置中的面部搜索和检测
公开(公告)号：WO2008107002A1
公开(公告)日：2008-09-12
申请号：PCT/EP2007/006540
申请日：2007-07-23
申请人： FOTONATION VISION LIMITED , STEINBERG, Eran , BIGIOI, Petronel , CORCORAN, Peter , GANGEA, Mihnea , PETRESCU, Stefan, Mirel , VASILIU, Andrei , COSTACHE, Gabriel , DRIMBAREAN, Alexandru
发明人： STEINBERG, Eran , BIGIOI, Petronel , CORCORAN, Peter , GANGEA, Mihnea , PETRESCU, Stefan, Mirel , VASILIU, Andrei , COSTACHE, Gabriel , DRIMBAREAN, Alexandru
IPC分类号： G06K9/00
CPC分类号： G06K9/46 , G06K9/00221 , G06K9/00228 , G06K9/00234 , G06K9/00241 , G06K9/00268 , G06K9/00288
摘要： A method of detecting a face in an image includes performing face detection within a first window of the image at a first location. A confidence level is obtained from the face detection indicating a probability of the image including a face at or in the vicinity of the first location. Face detection is then performed within a second window at a second location, wherein the second location is determined based on the confidence level.
摘要翻译：检测图像中的脸部的方法包括在第一位置处在图像的第一窗口内执行面部检测。从面部检测获得的置信水平，其指示包括在第一位置处或附近的脸部的图像的概率。然后在第二位置的第二窗口内执行面部检测，其中基于置信水平确定第二位置。

66. 发明申请

WO2008104549A2 SEPARATING DIRECTIONAL LIGHTING VARIABILITY IN STATISTICAL FACE MODELLING BASED ON TEXTURE SPACE DECOMPOSITION 审中-公开
标题翻译：基于纹理空间分解的统计面建模中的分离方向照明变化
公开(公告)号：WO2008104549A2
公开(公告)日：2008-09-04
申请号：PCT/EP2008/052329
申请日：2008-02-26
申请人： FOTONATION VISION LIMITED , IONITA, Mircea , BACIVAROV, Ioana , CORCORAN, Peter
发明人： IONITA, Mircea , BACIVAROV, Ioana , CORCORAN, Peter
CPC分类号： G06K9/40 , G06K9/00 , G06K9/00268 , G06K9/00281 , G06K9/4661 , G06K9/621 , G06T5/007 , H04N5/2351 , H04N5/2354
摘要： A technique for determining a characteristic of a face or certain other object within a scene captured in a digital image including acquiring an image and applying a linear texture model that is constructed based on a training data set and that includes a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations. A fit of the model to the face or certain other object is obtained including adjusting one or more individual values of one or more of the model components of the linear texture model. Based on the obtained fit of the model to the face or certain other object in the scene, a characteristic of the face or certain other object is determined.
摘要翻译：一种用于确定在数字图像中捕获的场景内的面部或某些其他对象的特征的技术，包括获取图像并应用基于训练数据集构建的线性纹理模型，并且包括一类对象，包括第一表现出对定向照明变化的依赖性的模型组件的子集以及独立于定向照明变化的模型组件的第二子集。获得模型对脸部或某些其他对象的拟合，包括调整线性纹理模型的一个或多个模型分量的一个或多个单独值。基于所获得的模型对场景中的面部或某些其他对象的拟合，确定脸部或某些其他对象的特征。

67. 发明申请

WO2008102205A2 DETECTION OF AIRBORNE FLASH ARTIFACTS USING PREFLASH IMAGE 审中-公开
标题翻译：使用PREFLASH图像检测AIRBORNE FLASH ARTIFACTS
公开(公告)号：WO2008102205A2
公开(公告)日：2008-08-28
申请号：PCT/IB2007/004431
申请日：2007-08-09
申请人： FOTONATION VISION LIMITED , CORCORAN, Peter , STEINBERG, Eran , DRIMBAREAN, Alexandru , VERTAN, Contantin , ZAMFIR, Adrian
发明人： CORCORAN, Peter , STEINBERG, Eran , DRIMBAREAN, Alexandru , VERTAN, Contantin , ZAMFIR, Adrian
CPC分类号： G06K9/40 , G06K9/4633 , G06T5/002 , G06T5/008 , G06T5/40 , G06T7/11 , G06T7/136 , G06T2207/20032
摘要： Flash image orb artifacts arising from specular reflections from airborne particles are corrected. An image of a scene using flash illumination and a reference image of substantially the same scene are acquired. The reference and flash images are subtracted to generate a difference image. Edge and interior region features of an orb artifact within the difference image are determined. The edge feature is matched with the interior region, and the orb artifact is corrected from the flash image based on the matching.
摘要翻译：来自空气中颗粒的镜面反射产生的闪光图像球体伪像被校正。获取使用闪光照明的场景的图像和基本上相同的场景的参考图像。减去参考和闪光图像以产生差分图像。确定差异图像内的球体伪像的边缘和内部区域特征。边缘特征与内部区域匹配，并且基于匹配从闪光图像校正球体伪影。

68. 发明申请

WO2008023280A2 ADVANCES IN EXTENDING THE AAM TECHNIQUES FROM GRAYSCALE TO COLOR IMAGES 审中-公开
标题翻译： AAM技术从灰度扩展到彩色图像的研究进展
公开(公告)号：WO2008023280A2
公开(公告)日：2008-02-28
申请号：PCT/IB2007/003724
申请日：2007-06-12
申请人： FOTONATION VISION LIMITED , IONITA, MIRCEA , CORCORAN, PETER
发明人： IONITA, MIRCEA , CORCORAN, PETER
CPC分类号： G06K9/00 , G06K9/00234 , G06K9/621
摘要： A face detection and/or detection method includes acquiring a digital color image. An active appearance model (AAM) is applied including an interchannel-decorrelated color space. One or more parameters of the model are matched to the image. Face detection results based on the matching and/or different results incorporating the face detection result are communicated.
摘要翻译：脸部检测和/或检测方法包括获取数字彩色图像。应用主动外观模型（AAM），其包括与声道间相关的色彩空间。模型的一个或多个参数与图像匹配。传达基于匹配和/或结合脸部检测结果的不同结果的脸部检测结果。

69. 发明申请

WO2007143415A2 IMAGE ACQUISITION METHOD AND APPARATUS 审中-公开
标题翻译：图像采集方法和设备
公开(公告)号：WO2007143415A2
公开(公告)日：2007-12-13
申请号：PCT/US2007069638
申请日：2007-06-26
申请人： FOTONATION VISION LTD , CORCORAN PETER , STEINBERG ERAN , BIGIOI PETRONEL , DRIMBAREAN ALEXANDER , ZAMFIR ADRIAN , FLOREA CORNELIU
发明人： CORCORAN PETER , STEINBERG ERAN , BIGIOI PETRONEL , DRIMBAREAN ALEXANDER , ZAMFIR ADRIAN , FLOREA CORNELIU
IPC分类号： G06K9/00 , H04N5/76
CPC分类号： H04N5/23251 , H04N5/23248 , H04N5/23258 , H04N5/23277
摘要： An image acquisition sensor of a digital image acquisition apparatus is coupled to imaging optics for acquiring a sequence of images. Images acquired by the sensor are stored. A motion detector causes the sensor to cease capture of an image when the degree of movement in acquiring the image exceeds a threshold. A controller selectively transfers acquired images for storage. A motion extractor determines motion parameters of a selected, stored image. An image re-constructor corrects the selected image with associated motion parameters. A selected plurality of images nominally of the same scene are merged and corrected by the image re- constructor to produce a high quality image of the scene.
摘要翻译：数字图像获取装置的图像采集传感器耦合到成像光学器件，用于获取图像序列。存储由传感器获取的图像。当获取图像的移动程度超过阈值时，运动检测器使得传感器停止图像的捕获。控制器选择性地传送获取的图像以进行存储。运动提取器确定所选存储的图像的运动参数。图像重建器使用关联的运动参数校正所选择的图像。通过图像重构装置合并和校正了名义上相同场景的所选择的多个图像，以产生高质量的场景图像。

70. 发明申请

WO2007073781A1 DIGITAL IMAGE ACQUISITION SYSTEM WITH PORTRAIT MODE 审中-公开
标题翻译：具有肖像模式的数字图像采集系统
公开(公告)号：WO2007073781A1
公开(公告)日：2007-07-05
申请号：PCT/EP2006/007573
申请日：2006-07-31
申请人： FOTONATION VISION LIMITED , STEINBERG, Eran , CORCORAN, Peter , BLONK, Leendert
发明人： STEINBERG, Eran , CORCORAN, Peter , BLONK, Leendert
IPC分类号： H04N5/272
CPC分类号： H04N5/272
摘要： A digital image acquisition system having no photographic film comprises an apparatus for capturing digital images and a flash unit for providing illumination during image capture. The system has a portrait mode for generating an image of a foreground object against a blurred background, the portrait mode being operable to capture first, second and third images (A, B and C) of nominally the same scene. One of the first and second images (A, B) is taken with flash and the other is taken without flash, and the third image (C) is blurred compared to the first and second images. The portrait mode is further operable to determine foreground and background regions of the scene using the first and second images (A, B) , and to substitute the blurred background of the third image (C) for the background of an in-focus image of the scene. In one embodiment the in-focus image is one of the first and second images. In another embodiment the in-focus image is a fourth image .
摘要翻译：没有摄影胶片的数字图像采集系统包括用于捕获数字图像的装置和用于在图像捕获期间提供照明的闪光单元。系统具有用于生成针对模糊背景的前景物体的图像的肖像模式，肖像模式可操作以捕获名义上相同的场景的第一，第二和第三图像（A，B和C）。第一和第二图像（A，B）中的一个用闪光拍摄，而另一个被拍摄而不闪光，并且第三图像（C）与第一和第二图像相比模糊。肖像模式还可操作以使用第一和第二图像（A，B）来确定场景的前景和背景区域，并且将第三图像（C）的模糊背景替换为现场。在一个实施例中，对焦图像是第一和第二图像之一。在另一个实施例中，对焦图像是第四图像。

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