公开(公告)号：US20120224784A1

公开(公告)日：2012-09-06

申请号：US13038094

申请日：2011-03-01

申请人： Noy Cohen ,  Jeffrey Danowitz ,  Orly Liba

发明人： Noy Cohen ,  Jeffrey Danowitz ,  Orly Liba

IPC分类号： G06K9/40

CPC分类号： G06T5/002 ,  G06T2207/20192

摘要： In accordance with an embodiment of the invention, an anisotropic denoising method is provided that removes sensor noise from a digital image while retaining edges, lines, and details in the image. In one embodiment, the method removes noise from a pixel of interest based on the detected type of image environment in which the pixel is situated. If the pixel is situated in an edge/line image environment, then denoising of the pixel is increased such that relatively stronger denoising of the pixel occurs along the edge or line feature. If the pixel is situated in a detail image environment, then denoising of the pixel is decreased such that relatively less denoising of the pixel occurs so as to preserve the details in the image. In one embodiment, detection of the type of image environment is accomplished by performing simple arithmetic operations using only pixels in a 9 pixel by 9 pixel matrix of pixels in which the pixel of interest is situated. As a result, improved image environment sensitive noise reduction is achieved that requires a relatively low gate count in hardware implementations.

摘要翻译： 根据本发明的实施例，提供了一种各向异性去噪方法，其从数字图像中去除传感器噪声，同时保留图像中的边缘，线和细节。 在一个实施例中，该方法基于所检测到的像素所在的图像环境的类型来从感兴趣的像素中去除噪声。 如果像素位于边缘/线图像环境中，则增加像素的去噪，使得像素的相对较强的去噪沿边缘或线特征发生。 如果像素位于细节图像环境中，则减小像素的去噪，使得像素的去噪相对较少，以便保留图像中的细节。 在一个实施例中，通过仅使用感兴趣像素所在的像素的9像素×9像素矩阵中的像素执行简单的算术运算来实现对图像环境的类型的检测。 结果，实现了改进的图像环境敏感的降噪，其在硬件实现中需要较低的门计数。

公开(公告)号：US06544805B2

公开(公告)日：2003-04-08

申请号：US09931731

申请日：2001-08-16

申请人： Ido Holcman ,  Alexander Shulman ,  Jeffrey Danowitz

发明人： Ido Holcman ,  Alexander Shulman ,  Jeffrey Danowitz

IPC分类号： H01L2166

CPC分类号： H01L22/34 ,  H01L2223/54493

摘要： A method for determining the orientation of a pattern on the surface of an object relative to the object. The pattern comprises an array of generally perpendicular grid lines intersecting at grid junctions, and the object comprises a marker located at an edge thereof. The method comprises: determining the directions of the grid lines relative to the direction of the reference coordinate system, determining the direction of object's orientation axis relative to the direction of the reference coordinate system, and determining the orientation of the grid lines relative to the object's orientation axis. The step of determining the direction of object's orientation axis comprises the steps of determining a location of the geometrical center of the object in the reference coordinate system and detecting and determining a location of the marker in the reference coordinate system.

公开(公告)号：US20140267826A1

公开(公告)日：2014-09-18

申请号：US13797898

申请日：2013-03-12

申请人： JEFFREY DANOWITZ ,  SARIT SHWARTZ ,  ZIV AVIV ,  DAVID STANHILL

发明人： JEFFREY DANOWITZ ,  SARIT SHWARTZ ,  ZIV AVIV ,  DAVID STANHILL

IPC分类号： H04N5/235

CPC分类号： H04N5/235 ,  H04N5/23229 ,  H04N9/735

摘要： An apparatus may include an image sensor that contains a multiplicity of pixel elements to detect one or more images and a processor circuit coupled to the image sensor. The apparatus may include a white balance module for execution on the processor circuit to receive, based upon a detected image of the one or more images, for a plurality of pixel elements of the multiplicity of pixel elements, three of more gray level values for a respective three or more color channels, to determine grayness likelihood functions for the respective three or more color channels, the three or more grayness likelihood functions comprising a proportional contribution to grey pixels of the detected image from one or more gray levels for each respective color channel, and to determine a white balance gain for two or more color channels based upon the determined grayness likelihood functions. Other embodiments are described and claimed.

摘要翻译： 装置可以包括图像传感器，其包含用于检测一个或多个图像的多个像素元件和耦合到图像传感器的处理器电路。 该装置可以包括用于在处理器电路上执行的白平衡模块，用于基于对于多个像素元素的多个像素元素的一个或多个图像的检测图像来接收三个以上的灰度级值 相应的三个或更多个颜色通道，以确定相应的三个或更多个颜色通道的灰度似然函数，所述三个或更多个灰度似然函数包括对于每个相应颜色通道的来自一个或多个灰度级的所检测图像的灰度像素的比例贡献 并且基于所确定的灰度似然函数来确定两个或更多个颜色通道的白平衡增益。 描述和要求保护其他实施例。

公开(公告)号：US07860280B2

公开(公告)日：2010-12-28

申请号：US11449849

申请日：2006-06-09

申请人： Jeffrey Danowitz

发明人： Jeffrey Danowitz

IPC分类号： G06K9/00 ,  G06K9/66

CPC分类号： G06K9/00281 ,  G06K9/00234 ,  G06K9/44 ,  G06K9/4647

摘要： A method for facial feature detection. The method comprises the following steps: a) receiving a digital image depicting a human face, the digital image comprising a plurality of color pixels, each one of the color pixels comprising color information, b) segmenting a face segment based on the color information, the face segment delimiting the area of the face, c) identifying a centerline that approximately bisects a human face section, and d) using the centerline to segment a set of facial features of the human face.

摘要翻译： 面部特征检测方法。 该方法包括以下步骤：a）接收描绘人脸的数字图像，所述数字图像包括多个彩色像素，所述彩色像素中的每一个包括颜色信息，b）基于所述颜色信息分割面部片段， 面部区域限定面部区域，c）识别近似平分人脸部分的中心线，以及d）使用中心线来分割人脸的一组面部特征。

公开(公告)号：US08879841B2

公开(公告)日：2014-11-04

申请号：US13038094

申请日：2011-03-01

申请人： Noy Cohen ,  Jeffrey Danowitz ,  Orly Liba

发明人： Noy Cohen ,  Jeffrey Danowitz ,  Orly Liba

IPC分类号： G06K9/00 ,  G06T5/00

CPC分类号： G06T5/002 ,  G06T2207/20192

摘要： In accordance with an embodiment of the invention, an anisotropic denoising method is provided that removes sensor noise from a digital image while retaining edges, lines, and details in the image. In one embodiment, the method removes noise from a pixel of interest based on the detected type of image environment in which the pixel is situated. If the pixel is situated in an edge/line image environment, then denoising of the pixel is increased such that relatively stronger denoising of the pixel occurs along the edge or line feature. If the pixel is situated in a detail image environment, then denoising of the pixel is decreased such that relatively less denoising of the pixel occurs so as to preserve the details in the image. In one embodiment, detection of the type of image environment is accomplished by performing simple arithmetic operations using only pixels in a 9 pixel by 9 pixel matrix of pixels in which the pixel of interest is situated. As a result, improved image environment sensitive noise reduction is achieved that requires a relatively low gate count in hardware implementations.

摘要翻译： 根据本发明的实施例，提供了一种各向异性去噪方法，其从数字图像中去除传感器噪声，同时保留图像中的边缘，线和细节。 在一个实施例中，该方法基于所检测到的像素所在的图像环境的类型来从感兴趣的像素中去除噪声。 如果像素位于边缘/线图像环境中，则增加像素的去噪，使得像素沿着边缘或线特征发生相对较强的去噪。 如果像素位于细节图像环境中，则减小像素的去噪，使得像素的去噪相对较少，以便保留图像中的细节。 在一个实施例中，通过仅使用感兴趣像素所在的像素的9像素×9像素矩阵中的像素执行简单的算术运算来实现对图像环境的类型的检测。 结果，实现了改进的图像环境敏感的降噪，其在硬件实现中需要较低的门计数。

公开(公告)号：US08687894B2

公开(公告)日：2014-04-01

申请号：US12905367

申请日：2010-10-15

申请人： Orly Liba ,  Noy Cohen ,  Jeffrey Danowitz

发明人： Orly Liba ,  Noy Cohen ,  Jeffrey Danowitz

IPC分类号： G06K9/48 ,  G06K9/56

CPC分类号： G06T7/44

摘要： In an embodiment, a device comprises a plurality of elements configured to apply a filter to multiple groups of pixels in a neighborhood of pixels surrounding a particular pixel to generate a matrix of filtered values; compute, from the matrix of filtered values, a first set of gradients along a first direction and a second set of gradients along a second and different direction; determine how many directional changes are experienced by the gradients in the first set of gradients and the gradients in the second set of gradients; compute a first weighted value for a first direction and a second weighted value for a second direction; and based, at least in part, upon the first and second weighted values, compute an overall texture characterization value for the particular pixel, wherein the overall texture characterization value indicates a type of image environment in which the particular pixel is located.

摘要翻译： 在一个实施例中，设备包括多个元件，其被配置为将滤波器应用于围绕特定像素的像素周围的多个像素组，以生成滤波值的矩阵; 从滤波值的矩阵中计算沿着第一方向的第一梯度梯度和沿着第二方向和不同方向的第二梯度集合; 确定第一组梯度中的梯度和第二组梯度中的梯度经历了多少方向变化; 计算第一方向的第一加权值和第二方向的第二加权值; 并且至少部分地基于第一和第二加权值来计算特定像素的总体纹理表征值，其中整体纹理表征值指示特定像素所在的图像环境的类型。

公开(公告)号：US20070286490A1

公开(公告)日：2007-12-13

申请号：US11449849

申请日：2006-06-09

申请人： Jeffrey Danowitz

发明人： Jeffrey Danowitz

IPC分类号： G06K9/46 ,  G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/00234 ,  G06K9/44 ,  G06K9/4647

摘要： A method for facial feature detection. The method comprises the following steps: a) receiving a digital image depicting a human face, the digital image comprising a plurality of color pixels, each one of the color pixels comprising color information, b) segmenting a face segment based on the color information, the face segment delimiting the area of the face, c) identifying a centerline that approximately bisects a human face section, and d) using the centerline to segment a set of facial features of the human face.

摘要翻译： 面部特征检测方法。 该方法包括以下步骤：a）接收描绘人脸的数字图像，所述数字图像包括多个彩色像素，所述彩色像素中的每一个包括颜色信息，b）基于所述颜色信息分割面部片段， 面部区域限定面部区域，c）识别大致平分人脸部分的中心线，以及d）使用中心线来分割人脸的一组面部特征。

公开(公告)号：US08249334B2

公开(公告)日：2012-08-21

申请号：US12300086

申请日：2007-05-10

申请人： Tamir Berliner ,  Ziv Hendel ,  Alexander Shpunt ,  Jeffrey Danowitz ,  Dmitri Rais ,  Oren Mor ,  Michael Shpigelmacher

发明人： Tamir Berliner ,  Ziv Hendel ,  Alexander Shpunt ,  Jeffrey Danowitz ,  Dmitri Rais ,  Oren Mor ,  Michael Shpigelmacher

IPC分类号： G06K9/00

CPC分类号： G06K9/00362 ,  G06T7/12 ,  G06T7/246 ,  G06T2207/10028 ,  G06T2207/30196

摘要： A computer-implemented method includes receiving a depth map (30) of a scene containing a body of a humanoid subject (28). The depth map includes a matrix of pixels (32), each corresponding to a respective location in the scene and having a respective pixel value indicative of a distance from a reference location to the respective location. The depth map is segmented so as to find a contour (64) of the body. The contour is processed in order to identify a torso (70) and one or more limbs (76, 78, 80, 82) of the subject. An input is generated to control an application program running on a computer by analyzing a disposition of at least one of the identified limbs in the depth map.

摘要翻译： 计算机实现的方法包括接收包含人形主体（28）的主体的场景的深度图（30）。 深度图包括像素矩阵（32），每个像素对应于场景中的相应位置，并且具有指示从参考位置到相应位置的距离的相应像素值。 深度图被分割以找到身体的轮廓（64）。 处理轮廓以识别受试者的躯干（70）和一个或多个肢体（76,78,80,82）。 生成输入以通过分析深度图中所识别的肢体中的至少一个的配置来控制在计算机上运行的应用程序。

公开(公告)号：US20120093419A1

公开(公告)日：2012-04-19

申请号：US12905367

申请日：2010-10-15

申请人： Orly Liba ,  Noy Cohen ,  Jeffrey Danowitz

发明人： Orly Liba ,  Noy Cohen ,  Jeffrey Danowitz

IPC分类号： G06K9/48

CPC分类号： G06T7/44

摘要： In an embodiment, a device comprises a plurality of elements configured to apply a filter to multiple groups of pixels in a neighborhood of pixels surrounding a particular pixel to generate a matrix of filtered values; compute, from the matrix of filtered values, a first set of gradients along a first direction and a second set of gradients along a second and different direction; determine how many directional changes are experienced by the gradients in the first set of gradients and the gradients in the second set of gradients; compute a first weighted value for a first direction and a second weighted value for a second direction; and based, at least in part, upon the first and second weighted values, compute an overall texture characterization value for the particular pixel, wherein the overall texture characterization value indicates a type of image environment in which the particular pixel is located.

摘要翻译： 在一个实施例中，设备包括多个元件，其被配置为将滤波器应用于围绕特定像素的像素周围的多个像素组，以生成滤波值的矩阵; 从滤波值的矩阵中计算沿着第一方向的第一梯度梯度和沿着第二方向和不同方向的第二梯度集合; 确定第一组梯度中的梯度和第二组梯度中的梯度经历了多少方向变化; 计算第一方向的第一加权值和第二方向的第二加权值; 并且至少部分地基于第一和第二加权值来计算特定像素的总体纹理表征值，其中整体纹理表征值指示特定像素所在的图像环境的类型。

公开(公告)号：US20100034457A1

公开(公告)日：2010-02-11

申请号：US12300086

申请日：2007-05-10

申请人： Tamir Berliner ,  Ziv Hendel ,  Alexander Shpunt ,  Jeffrey Danowitz ,  Dmitri Rais ,  Oren Mor ,  Michael Shpigelmacher

发明人： Tamir Berliner ,  Ziv Hendel ,  Alexander Shpunt ,  Jeffrey Danowitz ,  Dmitri Rais ,  Oren Mor ,  Michael Shpigelmacher

IPC分类号： G06T15/00 ,  G06K9/00

CPC分类号： G06K9/00362 ,  G06T7/12 ,  G06T7/246 ,  G06T2207/10028 ,  G06T2207/30196

摘要： A computer-implemented method includes receiving a depth map (30) of a scene containing a body of a humanoid subject (28). The depth map includes a matrix of pixels (32), each corresponding to a respective location in the scene and having a respective pixel value indicative of a distance from a reference location to the respective location. The depth map is segmented so as to find a contour (64) of the body. The contour is processed in order to identify a torso (70) and one or more limbs (76, 78, 80, 82) of the subject. An input is generated to control an application program running on a computer by analyzing a disposition of at least one of the identified limbs in the depth map.

摘要翻译： 计算机实现的方法包括接收包含人形主体（28）的主体的场景的深度图（30）。 深度图包括像素矩阵（32），每个像素对应于场景中的相应位置，并且具有指示从参考位置到相应位置的距离的相应像素值。 深度图被分割以找到身体的轮廓（64）。 处理轮廓以识别受试者的躯干（70）和一个或多个肢体（76,78,80,82）。 生成输入以通过分析深度图中所识别的肢体中的至少一个的配置来控制在计算机上运行的应用程序。