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

US10061984B2 Processing an image to identify a metric associated with the image and/or to determine a value for the metric 有权
公开(公告)号：US10061984B2
公开(公告)日：2018-08-28
申请号：US15332534
申请日：2016-10-24
申请人： Accenture Global Solutions Limited
发明人： Uvaraj Balasundaram , Kamal Mannar , Andrew K. Musselman , Devanandan Subbarayalu
IPC分类号： G06K9/00 , G06T7/00 , G07F17/32
CPC分类号： G06K9/00718 , G06K9/00744 , G06K9/00771 , G06K9/4628 , G06T5/002 , G06T5/40 , G06T7/0004 , G06T7/12 , G06T7/136 , G06T7/143 , G06T7/248 , G06T7/74 , G06T2207/10016 , G06T2207/10024 , G06T2207/20036 , G06T2207/20056 , G06T2207/20081 , G06T2207/20084 , G06T2207/20152 , G06T2207/30112 , G06T2207/30196 , G06T2207/30232 , G07F17/3232 , G07F17/3241
摘要： A device may receive one or more images captured by an image capture system. The one or more images may depict one or more objects. The device may process the one or more images using one or more image processing techniques. The device may identify the one or more objects based on processing the one or more images. The device may identify a context of the one or more images based on the one or more objects depicted in the one or more images. The device may determine whether the one or more objects contribute to a value of one or more metrics associated with the context. The device may perform an action based on the value of the one or more metrics.

2. 发明授权

US09842406B2 System and method for determining colors of foreground, and computer readable recording medium therefor 有权
公开(公告)号：US09842406B2
公开(公告)日：2017-12-12
申请号：US15045441
申请日：2016-02-17
申请人： Hanwha Techwin Co., Ltd.
发明人： Shimin Yin , Hwalsuk Lee , Jayeong Ku
IPC分类号： G06K9/46 , G06T7/40 , G06T7/00 , G06T7/20
CPC分类号： G06T7/90 , G06K9/4652 , G06T7/11 , G06T7/194 , G06T7/215 , G06T2207/20152
摘要： Provided are a system and method for determining at least one color of a foreground and a computer readable recording medium therefor. The system includes: a motion detector configured to detect a motion region from an image of an area; and a color determiner configured to determine at least one color of the foreground included in the motion region based on a difference between at least one color of the motion region and at least one color of a background which is a region outside the motion region in the image, for displaying the foreground color with the foreground at a display device.

3. 发明授权

US09811921B2 Apparatus and method for processing a depth image 有权
公开(公告)号：US09811921B2
公开(公告)日：2017-11-07
申请号：US15026870
申请日：2015-11-05
申请人： BOE TECHNOLOGY GROUP CO., LTD.
发明人： Jibo Zhao , Xingxing Zhao , Xiaoli Jin
IPC分类号： G06K9/00 , G06T7/564 , G06T7/11 , G06T7/149 , G06T7/13 , G06T5/00 , H04N13/02
CPC分类号： G06T7/564 , G06T5/002 , G06T7/11 , G06T7/12 , G06T7/13 , G06T7/149 , G06T2207/10028 , G06T2207/20036 , G06T2207/20152 , H04N13/257 , H04N2013/0081
摘要： Embodiments of the present invention disclose method and apparatus for processing a depth image. The method comprises: obtaining the depth image and a captured image corresponding to the depth image; segmenting the depth image to obtain a plurality of segmentation units; calculating a corresponding depth reference value for each segmentation unit; determining a standard range of depth value for the each segmentation unit based on the corresponding depth reference value; and adjusting a depth value of each pixel of the depth image to the standard range of depth value corresponding to the segmentation unit in which the each pixel is located. The method and the apparatus of embodiments of the present invention can improve the quality of the depth image and cause the depth image to be easily identified.

4. 发明申请

US20170236290A1 METHODS AND SYSTEMS OF PERFORMING VIDEO OBJECT SEGMENTATION 有权
公开(公告)号：US20170236290A1
公开(公告)日：2017-08-17
申请号：US15045102
申请日：2016-02-16
申请人： Disney Enterprises, Inc.
发明人： Alexander Sorkine Hornung , Federico Perazzi , Oliver Wang
IPC分类号： G06T7/00 , G06T7/40 , G06K9/62 , G06K9/46 , G06K9/52 , G06K9/00
CPC分类号： G06T7/11 , G06K9/00765 , G06K9/469 , G06K9/6273 , G06K9/6297 , G06T7/143 , G06T7/162 , G06T7/194 , G06T7/215 , G06T7/269 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081 , G06T2207/20152 , G06T2207/30241
摘要： Techniques and systems are described for performing video segmentation using fully connected object proposals. For example, a number of object proposals for a video sequence are generated. A pruning step can be performed to retain high quality proposals that have sufficient discriminative power. A classifier can be used to provide a rough classification and subsampling of the data to reduce the size of the proposal space, while preserving a large pool of candidate proposals. A final labeling of the candidate proposals can then be determined, such as a foreground or background designation for each object proposal, by solving for a posteriori probability of a fully connected conditional random field, over which an energy function can be defined and minimized.

5. 发明申请

US20170076443A1 METHOD AND SYSTEM FOR HYBRID MESH SEGMENTATION 审中-公开
标题翻译：混合网格分割的方法和系统
公开(公告)号：US20170076443A1
公开(公告)日：2017-03-16
申请号：US14851332
申请日：2015-09-11
申请人： Carestream Health, Inc.
发明人： Wei Ye , Shoupu Chen , Xavier Ripoche , Delphine Reynard
IPC分类号： G06T7/00 , G06F3/0482 , G06F3/0484 , G06T17/20 , A61B5/00
CPC分类号： G06T7/0012 , A61B5/0084 , A61B5/0088 , A61B5/4547 , A61B5/7271 , A61B5/742 , A61C7/002 , A61C2007/004 , G06F3/0482 , G06F3/04847 , G06T7/12 , G06T7/155 , G06T17/20 , G06T2200/04 , G06T2207/20152 , G06T2207/30036 , G06T2207/30041
摘要： A computer-implemented method for generating a digital model of an individual intraoral component from a digital model of a patient's dentition obtains a 3-D digital mesh model of the patient's dentition and performs automatic tooth component segmentation operation on the obtained mesh model. Automated segmentation results display. Interactive segmentation of the automated segmentation results is performed according to an operator instruction. Segmentation results are displayed and stored.
摘要翻译：用于从患者牙列的数字模型生成个体口内成分的数字模型的计算机实现方法获得患者牙列的3-D数字网格模型，并对获得的网格模型进行自动牙齿分割操作。自动分割结果显示。根据操作员指令执行自动分割结果的交互式分割。分割结果显示和存储。

6. 发明授权

US09418420B2 System and method for automated detection of lung nodules in medical images 有权
标题翻译：用于医学图像中肺结节自动检测的系统和方法
公开(公告)号：US09418420B2
公开(公告)日：2016-08-16
申请号：US14643791
申请日：2015-03-10
申请人： THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
发明人： Matthew S. Brown
IPC分类号： G06K9/00 , G06T7/00 , G06K9/46 , G06K9/52 , G06K9/62 , A61B6/03 , A61B6/12 , A61B6/00
CPC分类号： G06T7/0012 , A61B6/032 , A61B6/12 , A61B6/50 , A61B6/5217 , G06K9/46 , G06K9/52 , G06K9/6267 , G06K2009/4666 , G06T7/11 , G06T7/136 , G06T7/155 , G06T7/187 , G06T7/62 , G06T2200/04 , G06T2207/10081 , G06T2207/20041 , G06T2207/20152 , G06T2207/30064 , G06T2207/30096
摘要： A system and method for automatically segmenting a computed tomography (CT) image of a patient's lung. The method includes the steps of segmenting the CT image to acquire one or more lung regions, intensity thresholding the lung regions to generate a mask region comprising high-intensity regions corresponding to anatomical structures within the lung regions, computing a Euclidean distance map of the mask region, performing watershed segmentation of the Euclidean distance map to generate one or more sub-regions, identifying a seed point for each sub region, growing candidate regions from the seed point of each sub-region, and classifying one or more candidate regions as a lung nodule based on one or more geometric features of the candidate regions.
摘要翻译：用于自动分割患者肺的计算机断层摄影（CT）图像的系统和方法。该方法包括以下步骤：分割CT图像以获取一个或多个肺区域，强度阈值肺部区域以产生包括对应于肺区域内的解剖结构的高强度区域的掩模区域，计算掩模的欧氏距离图区域，执行欧氏距离图的分水岭分割以生成一个或多个子区域，识别每个子区域的种子点，从每个子区域的种子点生长候选区域，以及将一个或多个候选区域分类为基于候选区域的一个或多个几何特征的肺结节。

7. 发明授权

US09396547B2 Output display for segmented digital volume representing porous media 有权
标题翻译：代表多孔介质的分段数字体积的输出显示
公开(公告)号：US09396547B2
公开(公告)日：2016-07-19
申请号：US14704995
申请日：2015-05-06
申请人： Ingrain, Inc.
发明人： Naum Derzhi , Jack Dvorkin , Qian Fang , Michael Suhrer
IPC分类号： G06K9/00 , G06T7/00 , G06T15/08
CPC分类号： G06T7/0081 , G06K9/00624 , G06T7/0004 , G06T7/11 , G06T15/08 , G06T2207/10081 , G06T2207/20041 , G06T2207/20152 , G06T2207/30108
摘要： A method for increasing the accuracy of a target property value derived from a rock sample is described in which the sample is scanned to obtain a three-dimensional tomographic digital image which can be processed to pore space and solid material phases through a segmentation process. A process is used which revises the segmented volume, e.g., by increasing pore space connectivity, in a manner affecting the target property value that would be derived. Another described method increases the accuracy with which a segmented volume represents a material sample having structure not adequately resolved in an original three-dimensional tomographic digital image. Further, a system for performing the processes, and a segmented digital volume which more accurately represents a sample of a porous media, are described.
摘要翻译：描述了一种用于提高从岩石样本得到的目标特性值的准确度的方法，其中扫描样本以获得可以通过分割处理来处理为孔隙空间和固体材料相的三维断层数字图像。使用这样的方法，其以影响将导出的目标属性值的方式修改分段体积，例如通过增加孔隙空间连通性。另一种描述的方法提高了分割体积表示在原始三维断层数字图像中具有未充分分辨的结构的材料样品的精度。此外，描述了用于执行处理的系统和更准确地表示多孔介质的样本的分段数字体积。

8. 发明授权

US09292933B2 Method and apparatus for shape based deformable segmentation of multiple overlapping objects 有权
标题翻译：用于多重重叠对象的基于形状的可变形分割的方法和装置
公开(公告)号：US09292933B2
公开(公告)日：2016-03-22
申请号：US13978763
申请日：2012-01-10
申请人： Anant Madabhushi , Sahirzeehan Ali
发明人： Anant Madabhushi , Sahirzeehan Ali
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0089 , G06K9/0014 , G06K9/34 , G06T7/12 , G06T7/149 , G06T2207/20081 , G06T2207/20116 , G06T2207/20124 , G06T2207/20152 , G06T2207/30024 , G06T2207/30096
摘要： The present invention provides a system and method for simultaneous variational and adaptive segmentation of single non-overlapping and multiple overlapping/occluded-objects in an image scene. The method according to the present invention synergistically combines shape priors with boundary and region-based active contours in a level set formulation with a watershed scheme for model initialization for identifying and resolving multiple object overlaps in an image scene. The method according to the present invention comprises learning a shape prior for a target object of interest and applying the shape prior into a hybrid active contour model to segment overlapping and non-overlapping objects simultaneously.
摘要翻译：本发明提供了用于在图像场景中单个非重叠和多个重叠/遮挡物体的同时变分和自适应分割的系统和方法。根据本发明的方法将形状先验与边界和基于区域的主动轮廓协同地结合在具有用于模型初始化的分水岭方案的水平集公式中，用于识别和解决图像场景中的多个对象重叠。根据本发明的方法包括：在感兴趣的目标对象之前先学习一种形状，并将该形状应用于混合有源轮廓模型之前同时分割重叠和非重叠对象。

9. 发明授权

US09235901B2 Method for locating an interproximal tooth region 有权
标题翻译：用于定位邻间牙齿区域的方法
公开(公告)号：US09235901B2
公开(公告)日：2016-01-12
申请号：US12578826
申请日：2009-10-14
申请人： Jiayong Yan , Wei Wang , Liangliang Pan , Victor C. Wong
发明人： Jiayong Yan , Wei Wang , Liangliang Pan , Victor C. Wong
IPC分类号： G06T7/00
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/155 , G06T2207/10064 , G06T2207/20152 , G06T2207/30036
摘要： A method for locating one or more interproximal tooth regions in a digital tooth image. The method can be executed at least in part on data processing hardware. The method includes generating the digital tooth image from a fluorescence image of one or more teeth and a reflectance image of the one or more teeth, so as to combine image data from the fluorescence and reflectance images. The digital tooth image has intensity values for pixels corresponding to the one or more teeth and background. The method identifies one or more tooth regions by processing the digital tooth image and locates the one or more interproximal tooth regions according to the one or more identified tooth regions.
摘要翻译：一种用于定位数字牙齿图像中的一个或多个邻间牙齿区域的方法。该方法至少部分地可以在数据处理硬件上执行。该方法包括从一个或多个齿的荧光图像和一个或多个齿的反射图像生成数字牙齿图像，以便组合来自荧光和反射图像的图像数据。数字牙齿图像具有对应于一个或多个牙齿和背景的像素的强度值。该方法通过处理数字牙齿图像来识别一个或多个牙齿区域，并且根据一个或多个识别的牙齿区域定位一个或多个邻间牙齿区域。

10. 发明申请

US20150278575A1 BIO-IMAGING METHOD 有权
标题翻译：生物成像方法
公开(公告)号：US20150278575A1
公开(公告)日：2015-10-01
申请号：US14441471
申请日：2013-11-07
申请人： BIOMÉRIEUX , COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
发明人： Loréne Allano , Guillaume Sutra , Lorette Munoz , Corine Fulchiron , Dominique Decaux , Frédéric Pinston
IPC分类号： G06K9/00 , G06T7/40 , G06T5/00 , G06T7/00
CPC分类号： G06K9/0014 , G06K9/00127 , G06K9/00134 , G06T5/005 , G06T7/0012 , G06T7/12 , G06T7/73 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/10056 , G06T2207/10152 , G06T2207/20061 , G06T2207/20076 , G06T2207/20152 , G06T2207/30024 , G06T2207/30242
摘要： A method for defining an isolation area around an object of interest in a cell culture vessel, the method comprising the steps of: obtaining one or more images of the cell culture vessel using one or more of a plurality of illumination sources, each illumination source being capable of illuminating the vessel from a different direction; selecting an image or combination of images for further processing; applying a circular object detection transformation to identify one or more objects of interest being substantially circular objects in the cell culture vessel, which circular objects of interest are representative of isolated colonies in the cell culture vessel and determining the center of an object of interest; applying a binarizing step to obtain a binarized image of the object of interest and other objects, wherein the center of the binarized image corresponds to the center of the object of interest; iteratively forming concentric circles with increasing radius, wherein the concentric circles are centered on the center of the binarized image; identifying coronas, wherein a corona is delimited by two circles having successive radius values; for each corona: determining the presence and the location of any other object located in the corona to determine the presence and the location of other objects; determining a clearance angle defining an angular sector free of other objects around the object of interest to define the isolation area around the object of interest.
摘要翻译：一种用于在细胞培养容器内定义感兴趣对象周围的隔离区域的方法，所述方法包括以下步骤：使用多个照明源中的一个或多个获得所述细胞培养容器的一个或多个图像，每个照明源为能够从不同的方向照射船只; 选择图像或图像组合进行进一步处理; 应用圆形物体检测变换来识别细胞培养容器中基本为圆形物体的一个或多个感兴趣对象，所述感兴趣的圆形物体代表细胞培养容器中的孤立菌落并确定感兴趣对象的中心; 应用二值化步骤来获得感兴趣对象和其他对象的二值化图像，其中二值化图像的中心对应于感兴趣对象的中心; 迭代地形成具有增加的半径的同心圆，其中同心圆以二值化图像的中心为中心; 识别冠状物，其中电晕由具有连续半径值的两个圆界定; 对于每个电晕：确定位于电晕中的任何其它物体的存在和位置，以确定其它物体的存在和位置; 确定间隙角，其限定围绕感兴趣对象的其他物体的角扇区，以限定感兴趣对象周围的隔离区域。

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