公开(公告)号：US20130182972A1

公开(公告)日：2013-07-18

申请号：US13349275

申请日：2012-01-12

申请人： Xiaochen JING ,  Hila Nachlieli ,  Carl Staelin ,  Doron Shaked ,  Smadar Shiffman ,  Jan Allebach

发明人： Xiaochen JING ,  Hila Nachlieli ,  Carl Staelin ,  Doron Shaked ,  Smadar Shiffman ,  Jan Allebach

IPC分类号： G06K9/36

CPC分类号： G06T7/001 ,  G06T2207/10024 ,  G06T2207/30144

摘要： In at least some examples, a system comprises a processor and a memory coupled to the processor. The memory stores an image defect visibility predictor that, when executed by the processor, compares an original image with a defect image and outputs a predicted defect visibility image (PDVI) that accounts for defect masking by the original image.

摘要翻译： 在至少一些示例中，系统包括处理器和耦合到处理器的存储器。 存储器存储图像缺陷可见度预测器，其在由处理器执行时将原始图像与缺陷图像进行比较，并输出考虑了原始图像的缺陷掩蔽的预测缺陷可见性图像（PDVI）。

公开(公告)号：US09378546B2

公开(公告)日：2016-06-28

申请号：US13349275

申请日：2012-01-12

申请人： Xiaochen Jing ,  Hila Nachlieli ,  Carl Staelin ,  Doron Shaked ,  Smadar Shiffman ,  Jan Allebach

发明人： Xiaochen Jing ,  Hila Nachlieli ,  Carl Staelin ,  Doron Shaked ,  Smadar Shiffman ,  Jan Allebach

IPC分类号： G06T7/00

CPC分类号： G06T7/001 ,  G06T2207/10024 ,  G06T2207/30144

摘要： In at least some examples, a system comprises a processor and a memory coupled to the processor. The memory stores an image defect visibility predictor that, when executed by the processor, compares an original image with a defect image and outputs a predicted defect visibility image (PDVI) that accounts for defect masking by the original image.

摘要翻译： 在至少一些示例中，系统包括处理器和耦合到处理器的存储器。 存储器存储图像缺陷可见度预测器，其在由处理器执行时将原始图像与缺陷图像进行比较，并输出考虑了原始图像的缺陷掩蔽的预测缺陷可见性图像（PDVI）。

公开(公告)号：US09736332B2

公开(公告)日：2017-08-15

申请号：US13308061

申请日：2011-11-30

申请人： Omri Shacham ,  Oren Haik ,  Smadar Shiffman ,  Oded Perry

发明人： Omri Shacham ,  Oren Haik ,  Smadar Shiffman ,  Oded Perry

IPC分类号： H04N1/40 ,  G06K15/00 ,  H04N1/38 ,  G06T5/00 ,  G06T7/194 ,  H04N1/64

CPC分类号： H04N1/38 ,  G06T5/002 ,  G06T7/194 ,  G06T2207/20021 ,  H04N1/642

摘要： A method includes obtaining an image of a document against a background. A bounding box that bounds a region of the image that is distinguishable from the background is found. Coordinates of a plurality of points of the distinguishable region are found, each point being a point of the distinguishable region that is closest to each corner of the bounding box. The document is identified within the image as a region of the image whose corners are defined by the found coordinates.

公开(公告)号：US06424732B1

公开(公告)日：2002-07-23

申请号：US09203299

申请日：1998-12-01

申请人： Smadar Shiffman ,  Sandy Napel

发明人： Smadar Shiffman ,  Sandy Napel

IPC分类号： G06K900

CPC分类号： G06K9/38 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/136 ,  G06T7/149 ,  G06T2207/10072 ,  G06T2207/30101

摘要： Segregating object images from an image is accomplished by a method that includes intensity thresholding and generating isolabel contour lines at image regions of constant image intensity. The shapes of the isolabel contours are quantified by calculating turning angle sequences. The turning angle sequences of contours compared to discern which contours to group and label as belonging to an object image. The method uses information obtained from intensity thresholding in combination with the inherent shapes of the object images to group isolabel contours and segregate the object images. The method is general and is used for segregating object images from continues images such as photographs and film. The method is extended to 3-dimensional image volumes and further includes modeling cross sections of object images as ellipses. An overlap criteria is used to group cross sectional object images in an images volume from 2-dimensional slices of the image volume. The method has applications in medical imaging and is particularly useful for segregating vessel tissue from an image volume, wherein the volume is constructed from digitized data acquisitions obtained using ultrasound, CT, and MR imaging techniques.

摘要翻译： 通过包括强度阈值处理和在恒定图像强度的图像区域生成等值线的方法来实现从图像分离对象图像。 通过计算转角序列量化分离轮廓轮廓的形状。 轮廓的转动角度序列与将要分组和标记为属于对象图像的轮廓进行比较。 该方法使用从强度阈值获得的信息与对象图像的固有形状结合来分组异色标记轮廓并分离对象图像。 该方法是一般的，并且用于将对象图像与诸如照片和胶片的连续图像隔离。 该方法扩展到三维图像体积，并进一步包括将对象图像的横截面建模为椭圆。 重叠标准用于对来自图像体积的二维切片的图像体积中的截面对象图像进行分组。 该方法在医学成像中具有应用，并且特别适用于将血管组织与图像体积隔离，其中，体积是由使用超声，CT和MR成像技术获得的数字化数据采集构成的。