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

WO2018232592A1 FULLY CONVOLUTIONAL INSTANCE-AWARE SEMANTIC SEGMENTATION 审中-公开
公开(公告)号：WO2018232592A1
公开(公告)日：2018-12-27
申请号：PCT/CN2017/089189
申请日：2017-06-20
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC. , WEI, Yichen
发明人： WEI, Yichen , DAI, Jifeng , HU, Han
IPC分类号： G06T7/12
CPC分类号： G06T7/11 , G06K9/3233 , G06K9/6292 , G06T7/143 , G06T7/194
摘要： Embodiments herein present a fully convolutional approach for instance-aware semantic segmentation. Embodiments herein, for a given visual image, locate predefined categories of objects therein and produce pixel masks for each object instance. One method embodiment includes receiving an image and generating a pixel-wise score map for a given region of interest within the received image for each pixel cell present therein. For each pixel cell within the region of interest, the method may detect whether the pixel cell belongs to an object to obtain a detection result and determine whether the pixel cell is inside an object instance boundary to obtain a segmentation result. The method may then fuse the results to obtain a result of inside or outside for each pixel cell and form at least one mask based on those values.

2. 发明申请

WO2017070920A1 SPOOFED FACE DETECTION 审中-公开
标题翻译： SPOOFED脸部检测
公开(公告)号：WO2017070920A1
公开(公告)日：2017-05-04
申请号：PCT/CN2015/093334
申请日：2015-10-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC , LI, Jinyu , WEN, Fang , WEI, Yichen , CONRAD, Michael John , CHU, Chun-Te , JAWAID, Aamir
发明人： LI, Jinyu , WEN, Fang , WEI, Yichen , CONRAD, Michael John , CHU, Chun-Te , JAWAID, Aamir
IPC分类号： G06K9/00
CPC分类号： G06K9/00899 , G06K9/4652 , G06K9/6269
摘要： Examples are disclosed herein that relate to detecting spoofed human faces. One example provides a computing device comprising a processor configured to compute a first feature distance between registered image data of a human face in a first spectral region and test image data of the human face in the first spectral region, compute a second feature distance between the registered image data and test image data of the human face in a second spectral region, compute a test feature distance between the test image data in the first spectral region and the test image data in the second spectral region, determine, based on a predetermined relationship, whether the human face to which the test image data in the first and second spectral regions corresponds is a real human face or a spoofed human face, and modify a behavior of the computing device.
摘要翻译：这里公开了与检测伪造的人脸有关的示例。一个示例提供了一种计算设备，该计算设备包括处理器，该处理器被配置为计算第一光谱区域中的人脸的登记图像数据与第一光谱区域中的人脸的测试图像数据之间的第一特征距离，计算第二特征距离在第二光谱区域中记录人脸的登记图像数据和测试图像数据，计算第一光谱区域中的测试图像数据和第二光谱区域中的测试图像数据之间的测试特征距离，基于预定关系，第一和第二光谱区域中的测试图像数据所对应的人脸是否是真人脸或欺骗人脸，并且修改计算设备的行为。

3. 发明申请

WO2015013908A1 GEODESIC SALIENCY USING BACKGROUND PRIORS 审中-公开
标题翻译：使用背景技术的地球物理学
公开(公告)号：WO2015013908A1
公开(公告)日：2015-02-05
申请号：PCT/CN2013/080491
申请日：2013-07-31
申请人： MICROSOFT CORPORATION , WEI, Yichen , WEN, Fang , SUN, Jian
发明人： WEI, Yichen , WEN, Fang , SUN, Jian
IPC分类号： G06T11/00
CPC分类号： G06T7/162 , G06K9/3233 , G06T7/11 , G06T7/136 , G06T7/194 , G06T2207/20164
摘要： Disclosed herein are techniques and systems for computing geodesic saliency of images using background priors. An input image may be segmented into a plurality of patches, and a graph associated with the image may be generated, the graph comprising nodes and edges. The nodes of the graph include nodes that correspond to the plurality of patches of the image plus an additional virtual background node that is added to the graph. The graph further includes edges that connect the nodes to each other, including internal edges between adjacent patches and boundary edges between those patches at the boundary of the image and the virtual background node. Using this graph, a saliency value, called the "geodesic" saliency, for each patch of the image is determined as a length of a shortest path from a respective patch to the virtual background node.
摘要翻译：这里公开了用于使用背景先验计算图像的测地学显着性的技术和系统。可以将输入图像分割成多个片段，并且可以生成与图像相关联的图形，该图形包括节点和边缘。图形的节点包括与图像的多个补丁相对应的节点以及添加到图形的附加虚拟背景节点。该图进一步包括将节点彼此连接的边缘，包括相邻补丁之间的内部边缘和图像边界处的虚拟背景节点之间的这些补丁之间的边界边缘。使用该图，对于图像的每个补丁，显着值（称为“测地线”）显着性被确定为从相应补丁到虚拟背景节点的最短路径的长度。

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