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

US08531504B2 System and method for 3D video stabilization by fusing orientation sensor readings and image alignment estimates 有权
标题翻译：通过定向传感器读数和图像对准估计来定义3D视频稳定的系统和方法
公开(公告)号：US08531504B2
公开(公告)日：2013-09-10
申请号：US12888712
申请日：2010-09-23
申请人： Oscar Nestares , Yoram Gat , Horst W. Haussecker , Igor V. Kozintsev
发明人： Oscar Nestares , Yoram Gat , Horst W. Haussecker , Igor V. Kozintsev
IPC分类号： H04N13/02 , H04N5/228 , G06K9/46 , G06K9/66 , G06K9/40
CPC分类号： H04N5/23254 , H04N5/23258 , H04N5/23267
摘要： Methods and systems to for generating high accuracy estimates of the 3D orientation of a camera within a global frame of reference. Orientation estimates may be produced from an image-based alignment method. Other orientation estimates may be taken from a camera-mounted orientation sensor. The alignment-derived estimates may be input to a high pass filter. The orientation estimates from the orientation sensor may be processed and input to a low pass filter. The outputs of the high pass and low pass filters are fused, producing a stabilized video sequence.
摘要翻译：用于在全球参考系中产生相机的3D取向的高精度估计的方法和系统。取向估计可以从基于图像的对准方法产生。可以从安装摄像机的方向传感器获取其他方位估计。对准导出的估计可以被输入到高通滤波器。来自方向传感器的方向估计可以被处理并输入到低通滤波器。高通滤波器和低通滤波器的输出被融合，产生稳定的视频序列。

2. 发明授权

US08139894B2 Automatic dominant orientation estimation in text images based on steerable filters 有权
标题翻译：基于可转向滤波器的文本图像中的自动主导方向估计
公开(公告)号：US08139894B2
公开(公告)日：2012-03-20
申请号：US11961648
申请日：2007-12-20
申请人： Oscar Nestares
发明人： Oscar Nestares
IPC分类号： G06K9/36
CPC分类号： G06K9/3208
摘要： Briefly, in accordance with one or more embodiments, an image processing system is capable of receiving an image containing text, applying optical character recognition to the image, and then audibly reproducing the text via text-to-speech synthesis. Prior to optical character recognition, an orientation corrector is capable of detecting an amount of angular rotation of the text in the image with respect to horizontal, and then rotating the image by an appropriate amount to sufficiently align the text with respect to horizontal for optimal optical character recognition. The detection may be performed using steerable filters to provide an energy versus orientation curve of the image data. A maximum of the energy curve may indicate the amount of angular rotation that may be corrected by the orientation corrector.
摘要翻译：简而言之，根据一个或多个实施例，图像处理系统能够接收包含文本的图像，对图像应用光学字符识别，然后通过文本到语音合成可听地再现文本。在光学字符识别之前，取向校正器能够检测图像中的文本相对于水平的角度旋转量，然后旋转图像适当的量以使文本相对于水平方向充分对齐以获得最佳光学字符识别。可以使用可转向滤波器来执行检测，以提供图像数据的能量对方向曲线。能量曲线的最大值可以指示可由取向校正器校正的角旋转量。

3. 发明授权

US07447382B2 Computing a higher resolution image from multiple lower resolution images using model-based, robust Bayesian estimation 有权
标题翻译：使用基于模型的鲁棒贝叶斯估计计算来自多个较低分辨率图像的较高分辨率图像
公开(公告)号：US07447382B2
公开(公告)日：2008-11-04
申请号：US10882723
申请日：2004-06-30
申请人： Oscar Nestares , Horst W. Haussecker , Scott M. Ettinger
发明人： Oscar Nestares , Horst W. Haussecker , Scott M. Ettinger
IPC分类号： G06K9/32
CPC分类号： G06T3/4053
摘要： A result higher resolution (HR) image of a scene given multiple, observed lower resolution (LR) images of the scene is computed using a Bayesian estimation image reconstruction methodology. The methodology yields the result HR image based on a Likelihood probability function that implements a model for the formation of LR images in the presence of noise. This noise is modeled by a probabilistic, non-Gaussian, robust function. Other embodiments are also described and claimed.
摘要翻译：使用贝叶斯估计图像重建方法计算场景给定多个观察到的较低分辨率（LR）图像的场景的更高分辨率（HR）图像。该方法产生基于似然概率函数的结果HR图像，其实现了在存在噪声的情况下形成LR图像的模型。该噪声由概率非高斯鲁棒函数建模。还描述和要求保护其他实施例。

4. 发明申请

US20080112630A1 DIGITAL VIDEO STABILIZATION BASED ON ROBUST DOMINANT MOTION ESTIMATION 审中-公开
标题翻译：基于稳健运动估计的数字视频稳定
公开(公告)号：US20080112630A1
公开(公告)日：2008-05-15
申请号：US11558131
申请日：2006-11-09
申请人： Oscar Nestares , Horst Haussecker
发明人： Oscar Nestares , Horst Haussecker
IPC分类号： G06K9/36
CPC分类号： H04N5/23267 , G06T7/277 , G06T2207/10016 , G06T2207/20076 , G06T2207/30241 , G06T2207/30244 , H04N5/144 , H04N5/21 , H04N5/23248 , H04N5/23254 , H04N19/527 , H04N19/61 , H04N19/80
摘要： Various embodiments for performing digital video stabilization based on robust dominant motion estimation are described. In one embodiment, an apparatus may receive an input image sequence and estimate dominant motion between neighboring images in the image sequence. The apparatus may use a robust estimator to automatically detect and discount outliers corresponding to independently moving objects. Other embodiments are described and claimed.
摘要翻译：描述了基于鲁棒的主动运动估计执行数字视频稳定的各种实施例。在一个实施例中，装置可以接收输入图像序列并估计图像序列中相邻图像之间的主要运动。该装置可以使用鲁棒的估计器来自动检测和折叠对应于独立移动物体的离群值。描述和要求保护其他实施例。

5. 发明申请

US20150326801A1 RECTIFICATION TECHNIQUES FOR HETEROGENEOUS CAMERA ARRAYS 有权
标题翻译：异构相机阵列的修复技术
公开(公告)号：US20150326801A1
公开(公告)日：2015-11-12
申请号：US14270687
申请日：2014-05-06
申请人： KALPANA SESHADRINATHAN , OSCAR NESTARES
发明人： KALPANA SESHADRINATHAN , OSCAR NESTARES
IPC分类号： H04N5/357 , G06T7/00
CPC分类号： G06T7/002 , G06T7/85 , G06T2207/30208 , H04N5/23238 , H04N5/247 , H04N5/2628 , H04N5/357 , H04N13/243 , H04N17/002
摘要： Rectification techniques for heterogeneous camera arrays are described. In one embodiment, for example, an apparatus may comprise logic, at least a portion of which is in hardware, the logic to receive a captured image array captured by a heterogeneous camera array, select a rectification process for application to the captured image array, identify a set of rectification maps for the selected rectification process, and apply the identified set of rectification maps to the captured image array to obtain a rectified image array. Other embodiments are described and claimed.
摘要翻译：描述异质相机阵列的整流技术。在一个实施例中，例如，设备可以包括其硬件中的至少一部分的逻辑，用于接收由异质摄像机阵列捕获的捕获图像阵列的逻辑，选择用于应用于所捕获的图像阵列的整流过程，识别所选整流过程的一组整流图，并将识别的整流图集合应用于捕获的图像阵列以获得整流图像阵列。描述和要求保护其他实施例。

6. 发明授权

US09148582B2 Method and system for perfect shot imaging from multiple images 有权
标题翻译：从多幅图像完美拍摄成像的方法和系统
公开(公告)号：US09148582B2
公开(公告)日：2015-09-29
申请号：US13538983
申请日：2012-06-29
申请人： Oscar Nestares , Kalpana Seshadrinathan , Maha El Choubassi , Richard T. Beckwith , Sung Hee Park
发明人： Oscar Nestares , Kalpana Seshadrinathan , Maha El Choubassi , Richard T. Beckwith , Sung Hee Park
IPC分类号： H04N5/235 , H04N5/265 , H04N5/232
CPC分类号： H04N5/2356 , H04N5/23222 , H04N5/2351 , H04N5/265
摘要： An image processing apparatus, system, and method to automatically determine a plurality of image acquisition settings for an scene; acquire a set of images of the scene, the set of images including multiple images acquired with a distinct plurality of the determined image acquisition settings; and generate a single image by combining the acquired set of images.
摘要翻译：一种用于自动确定场景的多个图像获取设置的图像处理设备，系统和方法; 获取一组场景的图像，该组图像包括用不同的多个确定的图像获取设置获取的多个图像; 并且通过组合获取的图像集合来生成单个图像。

7. 发明授权

US08471865B2 System, method and apparatus for an edge-preserving smooth filter for low power architecture 有权
标题翻译：用于低功耗架构的边缘保护平滑滤波器的系统，方法和装置
公开(公告)号：US08471865B2
公开(公告)日：2013-06-25
申请号：US12753350
申请日：2010-04-02
申请人： Jianping Zhou , Oscar Nestares , Sheethal Bhat , Madhu Athreya
发明人： Jianping Zhou , Oscar Nestares , Sheethal Bhat , Madhu Athreya
IPC分类号： G09G5/00 , G09G5/02 , G06K9/40 , G06K9/36 , G06T5/20
CPC分类号： G09G3/2059 , G06T5/002 , G06T5/20
摘要： Embodiments of an apparatus, system and method are described for an edge-preserving smooth filter for low power architecture. A weighted pixel sum may be determined based on a weight of a central pixel and a weight of one or more neighboring pixels. The weight sum for the central pixel may be set to a power of two. An output of the central pixel may be displayed based on the weight sum and the weighted pixel sum. Other embodiments are described and claimed.
摘要翻译：描述了用于低功率架构的边缘保持平滑滤波器的装置，系统和方法的实施例。加权像素和可以基于中心像素的权重和一个或多个相邻像素的权重来确定。中心像素的权重和可以设为2的幂。可以基于加权和和加权像素和来显示中心像素的输出。描述和要求保护其他实施例。

8. 发明授权

US08406568B2 Automatic dominant orientation estimation in text images based on steerable filters 有权
标题翻译：基于可转向滤波器的文本图像中的自动主导方向估计
公开(公告)号：US08406568B2
公开(公告)日：2013-03-26
申请号：US13425002
申请日：2012-03-20
申请人： Oscar Nestares
发明人： Oscar Nestares
IPC分类号： G06K9/36
CPC分类号： G06K9/3208
摘要： Briefly, in accordance with one or more embodiments, an image-processing system is capable of receiving an image containing text, applying optical character recognition to the image, and then audibly reproducing the text via text-to-speech synthesis. Prior to optical character recognition, an orientation corrector is capable of detecting an amount of angular rotation of the text in the image with respect to horizontal, and then rotating the image by an appropriate amount to sufficiently align the text with respect to horizontal for optimal optical character recognition. The detection may be performed using steerable filters to provide an energy versus orientation curve of the image data. A maximum of the energy curve may indicate the amount of angular rotation that may be corrected by the orientation corrector.
摘要翻译：简而言之，根据一个或多个实施例，图像处理系统能够接收包含文本的图像，对图像应用光学字符识别，然后通过文本到语音合成来可听地再现文本。在光学字符识别之前，取向校正器能够检测图像中的文本相对于水平的角度旋转量，然后旋转图像适当的量以使文本相对于水平方向充分对准以获得最佳光学字符识别。可以使用可转向滤波器来执行检测，以提供图像数据的能量对方向曲线。能量曲线的最大值可以指示可由取向校正器校正的角旋转量。

9. 发明申请

US20090169131A1 OCR MULTI-RESOLUTION METHOD AND APPARATUS 有权
标题翻译： OCR多分辨率方法和设备
公开(公告)号：US20090169131A1
公开(公告)日：2009-07-02
申请号：US11964590
申请日：2007-12-26
申请人： Oscar Nestares , Badusha Kalathiparambil
发明人： Oscar Nestares , Badusha Kalathiparambil
IPC分类号： G06K9/32 , G06K9/40
CPC分类号： G06K9/6857
摘要： In some embodiments, provided are procedures for processing images that may have different font sizes. In some embodiments, it involves OCR'ing with multiple passes at different resolutions.
摘要翻译：在一些实施例中，提供了用于处理可能具有不同字体大小的图像的程序。在一些实施例中，它涉及以不同分辨率的多次通过的OCR。

10. 发明申请

US20090161991A1 AUTOMATIC DOMINANT ORIENTATION ESTIMATION IN TEXT IMAGES BASED ON STEERABLE FILTERS 有权
标题翻译：基于可转换滤波器的文本图像中的自动主导方位估计
公开(公告)号：US20090161991A1
公开(公告)日：2009-06-25
申请号：US11961648
申请日：2007-12-20
申请人： Oscar Nestares
发明人： Oscar Nestares
IPC分类号： G06K9/32
CPC分类号： G06K9/3208
摘要： Briefly, in accordance with one or more embodiments, an image processing system is capable of receiving an image containing text, applying optical character recognition to the image, and then audibly reproducing the text via text-to-speech synthesis. Prior to optical character recognition, an orientation corrector is capable of detecting an amount of angular rotation of the text in the image with respect to horizontal, and then rotating the image by an appropriate amount to sufficiently align the text with respect to horizontal for optimal optical character recognition. The detection may be performed using steerable filters to provide an energy versus orientation curve of the image data. A maximum of the energy curve may indicate the amount of angular rotation that may be corrected by the orientation corrector.
摘要翻译：简而言之，根据一个或多个实施例，图像处理系统能够接收包含文本的图像，对图像应用光学字符识别，然后通过文本到语音合成可听地再现文本。在光学字符识别之前，取向校正器能够检测图像中的文本相对于水平的角度旋转量，然后旋转图像适当的量以使文本相对于水平方向充分对准以获得最佳光学字符识别。可以使用可转向滤波器来执行检测，以提供图像数据的能量对方向曲线。能量曲线的最大值可以指示可由取向校正器校正的角旋转量。

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