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. 发明申请

US20180032832A1 MULTI-ANGLE PRODUCT IMAGING DEVICE 审中-公开
公开(公告)号：US20180032832A1
公开(公告)日：2018-02-01
申请号：US15222993
申请日：2016-07-29
申请人： Conduent Business Services, LLC
发明人： Yi-Ting Shen , Riyad Twahir , Wencheng Wu , Dennis L. Venable , Charles D. Rizzolo , Thomas F. Wade , Daniel S. Hann , Adrien P. Cote
IPC分类号： G06K9/32 , H04N5/232 , G06T7/00 , G06K7/10 , H04N1/00 , G06K9/46 , G06K9/62 , G06F17/30 , H04N5/225 , G06K7/14
CPC分类号： G06K9/3208 , G06F17/3028 , G06K7/10722 , G06K7/10861 , G06K7/1443 , G06K9/4604 , G06K9/4661 , G06K9/6201 , G06T7/0042 , G06T7/0079 , G06T7/0085 , G06T7/10 , G06T7/13 , G06T7/194 , G06T7/73 , G06T2207/20144 , H04N1/00204 , H04N5/222 , H04N7/18 , H04N2201/0084
摘要： A system for acquiring multi-angle images of a product includes a workstation having a working surface for placing a product, a camera supporting member having a vertical axis, and an image capturing device movably attached to the camera supporting member so that it may move along the vertical axis of the camera supporting member. The system captures and analyzes a digital image of a product to detect the vertical center of the product, and adjusts the position of the image capturing device along the vertical axis so that the vertical center of the product is proximate to the vertical center of the image. The system may also have a turntable and additionally rotate the turntable at multiple capturing angles and capture one or more additional digital images of the product at various capturing angles and store the one or more additional images in a product database.

2. 发明授权

US09870614B1 Automatic 3D brain tumor segmentation and classification 有权
公开(公告)号：US09870614B1
公开(公告)日：2018-01-16
申请号：US15218986
申请日：2016-07-25
申请人： SONY CORPORATION
发明人： Chen-Rui Chou , Bi Song , Ming-Chang Liu
IPC分类号： G06T7/00 , G06K9/62 , A61B5/055 , A61B5/00 , G01R33/48
CPC分类号： G06T7/0012 , A61B5/055 , A61B5/7264 , A61B2576/00 , G01R33/4808 , G01R33/4828 , G06K9/6267 , G06T7/0079 , G06T7/11 , G06T7/187 , G06T2200/04 , G06T2207/10088 , G06T2207/20081 , G06T2207/20156 , G06T2207/30016 , G06T2207/30096
摘要： A fully automatic brain tumor segmentation and classification method and system improve the healthcare experience with machine intelligence. The automatic brain tumor segmentation and classification method and system utilize whole tumor segmentation and multi-class tumor segmentation to provide accurate analysis.

3. 发明授权

US09495752B2 Multi-bone segmentation for 3D computed tomography 有权
标题翻译：用于3D计算机断层扫描的多骨分割
公开(公告)号：US09495752B2
公开(公告)日：2016-11-15
申请号：US13953825
申请日：2013-07-30
申请人： Dijia Wu , Neil Birkbeck , Michal Sofka , Meizhu Liu , Shaohua Kevin Zhou
发明人： Dijia Wu , Neil Birkbeck , Michal Sofka , Meizhu Liu , Shaohua Kevin Zhou
IPC分类号： G06T7/00
CPC分类号： G06T7/0079 , G06T7/0012 , G06T7/11 , G06T7/143 , G06T2207/10072 , G06T2207/20041 , G06T2207/20076
摘要： Multiple object segmentation is performed for three-dimensional computed tomography. The adjacent objects are individually segmented. Overlapping regions or locations designated as belonging to both objects may be identified. Confidence maps for the individual segmentations are used to label the locations of the overlap as belonging to one or the other object, not both. This re-segmentation is applied for the overlapping local, and not other locations. Confidence maps in re-segmentation and application just to overlap locations may be used independently of each other or in combination.
摘要翻译：对三维计算机断层摄影进行多目标分割。相邻的对象被单独分段。可以识别指定为属于两个对象的重叠区域或位置。用于各个分段的置信图用于将重叠的位置标记为属于一个或另一个对象，而不是两者。这种重新分割被应用于重叠的本地，而不是其他位置。重新分割和应用恰好重叠位置的置信度图可以彼此独立地或组合地使用。

4. 发明授权

US09251592B2 Pixel object detection in digital images method and system 有权
标题翻译：数字图像方法和系统中的像素对象检测
公开(公告)号：US09251592B2
公开(公告)日：2016-02-02
申请号：US13834530
申请日：2013-03-15
申请人： Friedemann Wachsmuth , Richard Case
发明人： Friedemann Wachsmuth , Richard Case
IPC分类号： G06K9/46 , G06K9/66 , G06T7/00 , G06F3/0488
CPC分类号： G06T7/0079 , G06F3/04883 , G06F2203/04806 , G06K9/342 , G06K2009/6213 , G06T7/12 , G06T2200/24 , G06T2207/10024 , G06T2207/20096
摘要： A user touches a touch sensitive display or otherwise provides input comprising “stroke” gestures to trace areas which are to be the subject of post-processing functions. The stroke area is highlighted and can be added to or corrected by additional stroke and “erase” gestures. Pixel objects are detected proximate to the stroke area, with a precision based on the zoom level. Stroke gesture input may be received and pixel object determination may be performed in series or in parallel.
摘要翻译：用户触摸触敏显示器或以其他方式提供包括“笔划”手势的输入，以跟踪将成为后处理功能的对象的区域。笔画区域被突出显示，可以添加到或通过额外的笔画或“擦除”手势进行修正。像素对象被检测到靠近笔划区域，具有基于缩放级别的精度。可以接收中风手势输入，并且可以串联或并行地执行像素对象确定。

5. 发明授权

US09183636B1 Line segmentation method 有权
标题翻译：线分割方法
公开(公告)号：US09183636B1
公开(公告)日：2015-11-10
申请号：US14254096
申请日：2014-04-16
申请人： Frederic Collet , Jordi Hautot , Michel Dauw , Pierre De Muelenaere , Olivier Dupont , Gunter Hensges
发明人： Frederic Collet , Jordi Hautot , Michel Dauw , Pierre De Muelenaere , Olivier Dupont , Gunter Hensges
IPC分类号： G06K9/34 , G06T7/00
CPC分类号： G06T7/0079 , G06K9/344 , G06K9/348 , G06K9/68 , G06K2209/01 , G06T7/10 , G06T2207/30176
摘要： A line segmentation method which starts with determining a first starting point coordinate and generating a list of potential character widths dependent on a maximum character width stored in a database and on characteristics of the portion of the line of text corresponding to the maximum character width. The method determines a second portion of the line of text corresponding to the first starting point coordinate and the first width on the list of potential character widths. On the second portion, a classification method is applied providing a likelihood of error for the first width and a candidate character. The likelihood of error is compared with a first threshold determined by a trade-off between speed and accuracy, and if the likelihood of error corresponding to the first width is lower than the threshold value, the candidate character is selected as the character meaning that a segment is known.
摘要翻译：线分割方法，其以确定第一起点坐标并根据存储在数据库中的最大字符宽度以及对应于最大字符宽度的文本行的部分的特征来生成潜在字符宽度的列表开始。该方法确定对应于第一起点坐标的文本行的第二部分和潜在字符宽度列表上的第一宽度。在第二部分，应用分类方法提供第一宽度和候选字符的误差的可能性。将误差的可能性与通过速度和精度之间的权衡确定的第一阈值进行比较，并且如果与第一宽度相对应的误差的可能性低于阈值，则选择候选字符作为字符，这意味着a 段是已知的。

6. 发明申请

US20150262368A1 IMAGE PROCESSING APPARATUS AND SEGMENTATION METHOD 有权
标题翻译：图像处理装置和分割方法
公开(公告)号：US20150262368A1
公开(公告)日：2015-09-17
申请号：US14613967
申请日：2015-02-04
申请人： OMRON CORPORATION
发明人： Atsushi Irie , Hiromatsu Aoki , Takahiro Sato
IPC分类号： G06T7/00 , G06K9/00
CPC分类号： G06T7/0079 , G06K9/00228 , G06K9/00362 , G06K9/34 , G06T7/11 , G06T7/174 , G06T7/194 , G06T2207/10016 , G06T2207/30201
摘要： An image processing apparatus for extracting an area of a detection target from an image includes an image input section that acquires an image, an image generation section that generates a plurality of images with different resolutions from the image, and a segmentation section that performs segmentation using the plurality of images with the different resolutions. The segmentation section segments an image with a low resolution and then segmenting an image with a high resolution using, as a processing target area, an area in the image with the high resolution corresponding to an area near a boundary resulting from processing of the segmentation of the image with the low resolution.
摘要翻译：一种用于从图像中提取检测对象的区域的图像处理装置包括获取图像的图像输入部分，从该图像生成具有不同分辨率的多个图像的图像生成部分，以及使用具有不同分辨率的多个图像。分割部分以低分辨率分割图像，然后使用具有高分辨率的图像中的区域对应于由分割处理产生的边界附近的区域作为处理对象区域，以高分辨率分割图像具有低分辨率的图像。

7. 发明申请

US20150262367A1 Method and Apparatus for Image Segmentation Algorithm 有权
标题翻译：图像分割算法和方法
公开(公告)号：US20150262367A1
公开(公告)日：2015-09-17
申请号：US14206079
申请日：2014-03-12
申请人： Nokia Corporation
发明人： Klaus F. Doppler , Anish Mittal , Hoseok Chang
IPC分类号： G06T7/00 , G06T3/20 , G06T7/40 , G06T5/00 , G06T3/40 , G06T1/20 , G06T5/20 , G06K9/34 , G06T3/00
CPC分类号： G06T7/0079 , G06K9/34 , G06T1/20 , G06T3/0093 , G06T3/20 , G06T3/4023 , G06T5/002 , G06T5/20 , G06T7/11 , G06T7/187 , G06T2207/10004 , G06T2207/10016 , G06T2207/10024 , G06T2207/20012 , G06T2207/20112
摘要： Disclosed herein is a method. Cluster centers of an image are initialized. The image includes a plurality of pixels. Pixels of the plurality of pixels in a pattern are labeled. The cluster centers are recomputed based on the labeling of the plurality of pixels.
摘要翻译：本文公开了一种方法。图像的群集中心被初始化。图像包括多个像素。图案中的多个像素的像素被标记。基于多个像素的标记重新计算聚类中心。

8. 发明授权

US09117280B2 Determining images of article for extraction 有权
标题翻译：确定提取物品的图像
公开(公告)号：US09117280B2
公开(公告)日：2015-08-25
申请号：US14037177
申请日：2013-09-25
申请人： Microsoft Corporation
发明人： Yu Chen , Ruihua Song , Guangping Gao , Qian Zhang , Ming Liu , Raman Narayanan , Shelley Summer Gu , Yanti Aruswati Gouw
IPC分类号： G06K9/34 , G06T7/00 , G06K9/00
CPC分类号： G06T7/0079 , G06F3/14 , G06K9/00087 , G06K9/00711 , G11B27/28 , G11B27/34
摘要： A content application determines images of an article for extraction. The content application identifies an initial image associated with a content of the article. A caption and a credit line associated with the initial image is detected and the initial image is extracted along with the caption and the credit line. A second image of the article associated with a video is also detected and extracted along with the video. In addition, the content application extracts a slideshow detected within the article.
摘要翻译：内容应用程序确定用于提取的文章的图像。内容应用程序识别与文章的内容相关联的初始图像。检测到与初始图像相关联的标题和信用额度，并且与标题和信用额度一起提取初始图像。与视频相关联的文章的第二个图像也与视频一起被检测和提取。另外，内容应用程序提取在文章中检测到的幻灯片。

9. 发明授权

US09105094B2 Image layers navigation 有权
标题翻译：图像层导航
公开(公告)号：US09105094B2
公开(公告)日：2015-08-11
申请号：US14043639
申请日：2013-10-01
申请人： Adobe Systems Incorporated
发明人： Remon Tijssen
IPC分类号： G06K9/00 , G06T7/00
CPC分类号： G06T7/0079 , G06T11/00
摘要： In embodiments of image layers navigation, a canvas interface displays image segments of an image in different layers of the image. An image layers application is implemented to receive a position input of a canvas viewer control that encompasses one or more of the image segments of the image, and then determine the layers of the image that correspond to the image segments encompassed by the canvas viewer control. The position input of the canvas viewer control is effective to select the layers of the image that correspond to the one or more image segments encompassed by the canvas viewer control. Thumbnail images are then displayed that each represent one of the layers encompassed by the canvas viewer control, where each of the layers represented by a thumbnail image are displayed to include the image segments associated with a respective layer of the image.
摘要翻译：在图像层导航的实施例中，画布界面在图像的不同层中显示图像的图像片段。实现图像层应用以接收包含图像的一个或多个图像片段的画布浏览器控件的位置输入，然后确定与画布观看器控件所包含的图像片段相对应的图像层。画布查看器控件的位置输入对于选择与画布观看器控件所包含的一个或多个图像段对应的图像层是有效的。然后显示缩略图图像，每个图像表示由画布观看器控件包围的层之一，其中显示由缩略图图像表示的每个层以包括与图像的相应层相关联的图像片段。

10. 发明申请

US20140267375A1 STENCIL THEN COVER PATH RENDERING WITH SHARED EDGES 有权
标题翻译：然后用共享边缘覆盖路径渲染
公开(公告)号：US20140267375A1
公开(公告)日：2014-09-18
申请号：US14028421
申请日：2013-09-16
申请人： NVIDIA CORPORATION
发明人： Mark J. KILGARD , Jeffrey A. BOLZ
IPC分类号： G06T3/00
CPC分类号： G06T7/0079 , G06T1/20 , G06T1/60 , G06T3/0012 , G06T11/40
摘要： One embodiment of the present invention includes techniques for rasterizing primitives that include edges shared between paths. For each edge, a rasterizer unit selects and applies a sample rule from multiple sample rules. If the edge is shared, then the selected sample rule causes each group of coverage samples associated with a single color sample to be considered as either fully inside or fully outside the edge. Consequently, conflation artifacts caused when the number of coverage samples per pixel exceeds the number of color samples per pixel may be reduced. In prior-art techniques, reducing such conflation artifacts typically involves increasing the number of color samples per pixel to equal the number of coverage samples per pixel. Advantageously, the disclosed techniques enable rendering using algorithms that reduce the ratio of color to coverage samples, thereby decreasing memory consumption and memory bandwidth use, without causing conflation artifacts associated with shared edges.
摘要翻译：本发明的一个实施例包括用于光栅化包括在路径之间共享的边缘的图元的技术。对于每个边缘，光栅化器单元从多个样本规则中选择并应用样本规则。如果边缘是共享的，则所选择的样本规则使得与单个颜色样本相关联的每组覆盖样本被视为完全在边缘内部或完全在边缘外部。因此，当每像素的覆盖样本的数量超过每像素的颜色样本的数量时，引起的接合伪影可能被减少。在现有技术中，减少这种接合伪影通常涉及增加每像素的颜色样本的数量，以等于每像素的覆盖样本的数量。有利地，所公开的技术使得能够使用降低颜色与覆盖样本的比率的算法进行渲染，从而减少存储器消耗和存储器带宽使用，而不会引起与共享边缘相关联的协调伪影。

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