专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US08755608B2 Marker generation device, marker generation detection system, marker generation detection device, marker, marker generation method, and program therefor 有权
标题翻译：标记生成装置，标记生成检测系统，标记生成检测装置，标记，标记生成方法及其程序
公开(公告)号：US08755608B2
公开(公告)日：2014-06-17
申请号：US13386266
申请日：2010-07-22
申请人： Noboru Nakajima
发明人： Noboru Nakajima
IPC分类号： G06K9/46
CPC分类号： G06K9/468 , G06K2009/0059 , G06K2009/3225
摘要： Provided is a marker generation device which has a measurement means, an invariant feature conversion means, a singular feature selection means, and a marker generation means. The measurement means measures a change in posture of an object in a background image on the basis of the image. The invariant feature conversion means indicates feature points extracted from the background image in an invariant feature space by means of a predetermined conversion process in accordance with the change in posture. The singular feature selection means selects, as a singular feature, a part in which the feature points are not indicated in the invariant feature space. The marker generation means generates a marker with the use of the singular feature.
摘要翻译：提供了一种具有测量装置，不变特征转换装置，奇异特征选择装置和标记产生装置的标记产生装置。测量装置基于图像来测量背景图像中的对象的姿势变化。不变特征转换装置根据姿势变化通过预定的转换处理来指示从不变特征空间中的背景图像中提取的特征点。奇异特征选择装置选择在不变特征空间中未指示特征点的部分作为单个特征。标记生成装置使用奇异特征生成标记。

22. 发明授权

US08731304B2 Computer-readable storage medium storing image processing program, image processing method, and image processing device 有权
标题翻译：存储图像处理程序，图像处理方法和图像处理装置的计算机可读存储介质
公开(公告)号：US08731304B2
公开(公告)日：2014-05-20
申请号：US13403466
申请日：2012-02-23
申请人： Takayuki Baba , Shugo Nakamura , Masaki Ishihara , Masahiko Sugimura , Susumu Endo , Yusuke Uehara , Daiki Masumoto , Shigemi Nagata
发明人： Takayuki Baba , Shugo Nakamura , Masaki Ishihara , Masahiko Sugimura , Susumu Endo , Yusuke Uehara , Daiki Masumoto , Shigemi Nagata
IPC分类号： G06K9/46
CPC分类号： G06K9/468 , G06F17/3079
摘要： A computer-readable storage medium storing an image processing program that causes a computer to execute a process includes acquiring the same object identification information included in a plurality of image data items by referring to a storage unit that stores each of the image data items, object identification information that identifies an object included in the image data item, and a location information item that identifies a location of the object in the image data item in association with one another; acquiring the location of the object identified by the acquired object identification information in each of the image data items by referring to the storage unit; computing a difference between the acquired location information items; comparing the difference between the location information items with a predetermined location threshold value; and determining whether the image data items are to be in the same group.
摘要翻译：存储导致计算机执行处理的图像处理程序的计算机可读存储介质通过参照存储单元来获取包含在多个图像数据项中的相同对象标识信息，所述存储单元存储每个图像数据项目，对象识别包含在图像数据项中的对象的识别信息以及识别图像数据项中的对象的位置的位置信息项，彼此相关联; 通过参照存储单元来获取由所获取的对象识别信息识别的对象在每个图像数据项中的位置; 计算所获取的位置信息项之间的差; 将所述位置信息项之间的差与预定位置阈值进行比较; 以及确定图像数据项是否在同一组中。

23. 发明申请

US20140072208A1 SYSTEM AND METHOD FOR AUTOMATED OBJECT DETECTION IN AN IMAGE 有权
标题翻译：自动对象检测在图像中的系统和方法
公开(公告)号：US20140072208A1
公开(公告)日：2014-03-13
申请号：US14026730
申请日：2013-09-13
申请人： Los Alamos National Security, LLC
发明人： Garrett T. Kenyon , Steven P. Brumby , John S. George , Dylan M. Paiton , Peter F. Schultz
IPC分类号： G06K9/80 , G06K9/46
CPC分类号： G06K9/80 , G06K9/4604 , G06K9/4609 , G06K9/468 , G06K9/6211 , G06K9/6212
摘要： A contour/shape detection model may use relatively simple and efficient kernels to detect target edges in an object within an image or video. A co-occurrence probability may be calculated for two or more edge features in an image or video using an object definition. Edge features may be differentiated between in response to measured contextual support, and prominent edge features may be extracted based on the measured contextual support. The object may then be identified based on the extracted prominent edge features.
摘要翻译：轮廓/形状检测模型可以使用相对简单和有效的内核来检测图像或视频内的对象中的目标边缘。可以使用对象定义来计算图像或视频中的两个或更多个边缘特征的共现概率。可以在响应于测量的上下文支持之间区分边缘特征，并且可以基于所测量的上下文支持来提取突出边缘特征。然后可以基于所提取的突出边缘特征来识别对象。

24. 发明授权

US08620069B1 Automatic triangle orientation detection algrorithm 有权
标题翻译：自动三角形方位检测算法
公开(公告)号：US08620069B1
公开(公告)日：2013-12-31
申请号：US13025570
申请日：2011-02-11
申请人： Alan R. Pinkus , David W. Dommett , Harry Lee Task
发明人： Alan R. Pinkus , David W. Dommett , Harry Lee Task
IPC分类号： G06K9/00
CPC分类号： G06T7/0004 , G06K9/468 , G06T2207/10024 , G06T2207/30168
摘要： A method, apparatus and program product are presented for detecting an image. Ring contour images are created by blurring the image, posterizing the blurred image at a plurality of levels and creating the ring contour images from each of the posterized images. Convex hull images are created by creating a plurality of corner images from corners within the image located by at least two different corner algorithms, finding a bounding rectangle that encompasses the ring contour images, cropping the corner images using the bounding rectangle, applying a threshold to the cropped corner images, and creating the convex hull images by generating a convex hull from the corners in each of the cropped corner images. A plurality of triangles is created by fitting a triangle with an orientation to the ring contour images and the convex hull images. Finally the orientation of the triangle is determined from the plurality of triangles.
摘要翻译：提出了用于检测图像的方法，装置和程序产品。环形轮廓图像通过模糊图像，在多个级别上对模糊图像进行后缀并从每个后缀图像创建环形轮廓图像来创建。通过从由至少两个不同角算法定位的图像中的角落创建多个角图来创建凸体图像，找到包围环轮廓图像的边界矩形，使用边界矩形裁剪角图像，应用阈值裁剪的角落图像，以及通过从每个裁剪角图像中的角落生成凸包来创建凸包图像。通过将具有取向的三角形与环轮廓图像和凸包图像拟合来创建多个三角形。最后，从多个三角形确定三角形的取向。

25. 发明授权

US08571264B2 Method of using structural models for optical recognition 有权
标题翻译：使用结构模型进行光学识别的方法
公开(公告)号：US08571264B2
公开(公告)日：2013-10-29
申请号：US13209779
申请日：2011-08-15
申请人： Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
发明人： Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
IPC分类号： G06K9/00 , G06K9/34
CPC分类号： G06K9/6878 , G06K9/468 , G06K2209/01
摘要： A method and system for recognizing all varieties of objects in an image by using structure models are disclosed. Structural elements are sought when comparing a structural model with an image but only within a framework of one or more generated hypotheses. The method for identifying objects includes preliminarily creating a structural model of objects by specifying a plurality of basic geometric structural elements corresponding to one or more portions of the object, recording a spatial characteristic of each identified basic geometric structural element, and recording a relational characteristic for each specified basic geometric structural element. Objects in the image are isolated and a list of hypotheses for each object is provided. Hypotheses are tested by determining if the corresponding group of basic geometric structural elements corresponds to another supposed object described in a classifier. Results of testing of hypotheses may be saved and the results may be used to identify objects.
摘要翻译：公开了通过使用结构模型识别图像中的各种物体的方法和系统。当将结构模型与图像进行比较但仅在一个或多个生成的假设的框架内时，寻求结构元素。用于识别对象的方法包括通过指定与对象的一个或多个部分相对应的多个基本几何结构元素来初步创建对象的结构模型，记录每个识别的基本几何结构元素的空间特征，并且记录关系特征每个指定的基本几何结构元素。图像中的对象被隔离，并提供每个对象的假设列表。通过确定对应的基本几何结构元素组是否对应于分类器中描述的另一假定对象来测试假设。可以节省假设检验结果，结果可用于识别物体。

26. 发明申请

US20120321169A1 Shape Based Conditional Random Fields for Segmenting Intracranial Aneurysms 有权
标题翻译：基于形状的条件随机场分割颅内动脉瘤
公开(公告)号：US20120321169A1
公开(公告)日：2012-12-20
申请号：US13456542
申请日：2012-05-30
申请人： Sajjad Hussain Baloch , Erkang Cheng , Tong Fang , Ying Zhu
发明人： Sajjad Hussain Baloch , Erkang Cheng , Tong Fang , Ying Zhu
IPC分类号： G06K9/34
CPC分类号： G06T7/0083 , G06K9/4638 , G06K9/468 , G06K2209/05 , G06T7/12 , G06T7/143 , G06T7/149 , G06T2207/10072 , G06T2207/20076 , G06T2207/20124 , G06T2207/30101
摘要： A method for segmenting intracranial aneurysms in digital medical images includes extracting a mesh representing a vessel surface from a volumetric digital image, the mesh comprising a set of points {pi} and edges {eij} respective points, and finding a set of binary labelings that minimizes an energy functional of the labelings and of shape descriptors of each point in the mesh, where the binary labelings segments an aneurysm from the surface by associating one of two labels with each point pi, where a label indicates whether an associated point is on a vessel or on an aneurysm, where the energy functional includes a unary potential term summed over all points that represent a posterior distribution of the labels over the points, and a pairwise potential term summed over all edges that represents neighborhood labeling relationships.
摘要翻译：用于在数字医学图像中分割颅内动脉瘤的方法包括从体积数字图像中提取表示血管表面的网格，所述网格包括一组点{pi}和边缘{eij}各自的点，并且找到一组二进制标记，最小化网格中每个点的标签和形状描述符的能量功能，其中二进制标签通过将两个标签中的一个与每个点pi相关联来从表面分割动脉瘤，其中标签指示关联点是否在血管或动脉瘤，其中能量功能包括表示标记在点上的后验分布的所有点上的一元潜在项，以及表示邻域标记关系的所有边缘上的成对潜在项。

27. 发明授权

US08244044B2 Feature selection and extraction 有权
标题翻译：特征选择和提取
公开(公告)号：US08244044B2
公开(公告)日：2012-08-14
申请号：US12109347
申请日：2008-04-25
申请人： Gang Hua , Paul Viola , David Liu
发明人： Gang Hua , Paul Viola , David Liu
IPC分类号： G06K9/62 , G06K9/46
CPC分类号： G06K9/4647 , G06K9/468 , G06K9/6228
摘要： Image feature selection and extraction (e.g., for image classifier training) is accomplished in an integrated manner, such that higher-order features are merely developed from first-order features selected for image classification. That is, first-order image features are selected for image classification from an image feature pool, initially populated with pre-extracted first-order image features. The selected first-order classifying features are paired with previously selected first-order classifying features to generate higher-order features. The higher-order features are placed into the image feature pool as they are developed or “on-the-fly” (e.g., for use in image classifier training).
摘要翻译：图像特征选择和提取（例如，用于图像分类器训练）以集成的方式实现，使得仅从为图像分类选择的一阶特征开发高阶特征。也就是说，从图像特征池中选择用于图像分类的一阶图像特征，最初用预提取的一阶图像特征填充。所选择的一阶分类特征与先前选择的一阶分类特征配对以产生更高阶的特征。更高阶的特征被放置在图像特征池中，因为它们被开发或“即时”（例如，用于图像分类器训练）。

28. 发明申请

US20120114254A1 MARKER DETERMINATION DEVICE, MARKER DETERMINATION DETECTION SYSTEM, MARKER DETERMINATION DETECTION DEVICE, MARKER, MARKER DETERMINATION METHOD, AND PROGRAM THEREFOR 有权
标题翻译：标记确定装置，标记确定检测系统，标记确定检测装置，标记，标记确定方法及其程序
公开(公告)号：US20120114254A1
公开(公告)日：2012-05-10
申请号：US13386306
申请日：2010-07-22
申请人： Noboru Nakjima
发明人： Noboru Nakjima
IPC分类号： G06K9/46
CPC分类号： G06K9/468 , G06K2009/0059 , G06K2009/3225 , G06T1/0021
摘要： Provided is a marker judgment device which has a feature storage means and a feature comparison means. The feature storage means disposes feature points extracted from an image in a predetermined space, sets parts in which the number of feature points in the predetermined space is equal to or less than a predetermined number as singular features, and stores the singular features and feature points extracted from an existing mark. The feature comparison means disposes the feature points extracted from the existing mark in the predetermined space, and judges that the existing mark is capable of being used as a marker which is detectable from the image, when the number of feature points that coincide with the singular features is equal to or more than a predetermined number.
摘要翻译：提供一种具有特征存储装置和特征比较装置的标记判断装置。特征存储装置将从预定空间中的图像提取的特征点配置为将预定空间中的特征点的数量等于或小于预定数量的部分作为奇异特征，并存储单个特征和特征点从现有商标中提炼出来。特征比较装置将从现有标记提取的特征点放置在预定空间中，并且当与单数相符的特征点的数量时，判定现有标记能够被用作可从图像中检测到的标记特征等于或大于预定数量。

29. 发明申请

US20120114253A1 MARKER GENERATION DEVICE, MARKER GENERATION DETECTION SYSTEM, MARKER GENERATION DETECTION DEVICE, MARKER, MARKER GENERATION METHOD, AND PROGRAM THEREFOR 有权
标题翻译：标记生成装置，标记生成检测系统，标记生成检测装置，标记，标记生成方法及其程序
公开(公告)号：US20120114253A1
公开(公告)日：2012-05-10
申请号：US13386266
申请日：2010-07-22
申请人： Noboru Nakajima
发明人： Noboru Nakajima
IPC分类号： G06K9/46
CPC分类号： G06K9/468 , G06K2009/0059 , G06K2009/3225
摘要： Provided is a marker generation device which has a measurement means, an invariant feature conversion means, a singular feature selection means, and a marker generation means. The measurement means measures a change in posture of an object in a background image on the basis of the image. The invariant feature conversion means indicates feature points extracted from the background image in an invariant feature space by means of a predetermined conversion process in accordance with the change in posture. The singular feature selection means selects, as a singular feature, a part in which the feature points are not indicated in the invariant feature space. The marker generation means generates a marker with the use of the singular feature.
摘要翻译：提供了一种具有测量装置，不变特征转换装置，奇异特征选择装置和标记产生装置的标记产生装置。测量装置基于图像来测量背景图像中的对象的姿势变化。不变特征转换装置根据姿势变化通过预定的转换处理来指示从不变特征空间中的背景图像中提取的特征点。奇异特征选择装置选择在不变特征空间中未指示特征点的部分作为单个特征。标记生成装置使用奇异特征生成标记。

30. 发明申请

US20110311129A1 TRAINING-FREE GENERIC OBJECT DETECTION IN 2-D AND 3-D USING LOCALLY ADAPTIVE REGRESSION KERNELS 有权
标题翻译： 2-D和3-D使用本地自适应回归记录仪进行无训练的一般对象检测
公开(公告)号：US20110311129A1
公开(公告)日：2011-12-22
申请号：US12998965
申请日：2009-12-16
申请人： Peyman Milanfar , Hae Jong Seo
发明人： Peyman Milanfar , Hae Jong Seo
IPC分类号： G06K9/00
CPC分类号： G06K9/00335 , G06K9/4642 , G06K9/468
摘要： The present invention provides a method of learning-free detection and localization of actions that includes providing a query video action of interest and providing a target video, obtaining at least one query space-time localized steering kernel (3-D LSK) from the query video action of interest and obtaining at least one target 3-D LSK from the target video, determining at least one query feature from the query 3-D LSK and determining at least one target patch feature from the target 3-D LSK, and outputting a resemblance map, where the resemblance map provides a likelihood of a similarity between each the query feature and each target patch feature to output learning-free detection and localization of actions, where the steps of the method are performed by using an appropriately programmed computer.
摘要翻译：本发明提供了一种无学习检测和动作定位的方法，包括提供感兴趣的查询视频动作并提供目标视频，从查询中获取至少一个查询时空局部化导向内核（3-D LSK）视频动作，从目标视频获取至少一个目标3-D LSK，从查询3-D LSK确定至少一个查询特征，并从目标3-D LSK确定至少一个目标补丁特征，并输出相似图，其中相似图提供每个查询特征与每个目标补丁特征之间的相似性的可能性，以输出无学习的检测和动作的定位，其中通过使用适当编程的计算机来执行该方法的步骤。

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