专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US08848974B2 Object-tracking systems and methods 有权
标题翻译：对象跟踪系统和方法
公开(公告)号：US08848974B2
公开(公告)日：2014-09-30
申请号：US12240724
申请日：2008-09-29
申请人： Shehrzad A. Qureshi , Kyle R. Breton , John A. Tenney
发明人： Shehrzad A. Qureshi , Kyle R. Breton , John A. Tenney
IPC分类号： G06K9/00 , G06T7/20 , A61B19/00 , A61B17/00
CPC分类号： A61B34/10 , A61B34/20 , A61B34/30 , A61B34/32 , A61B90/17 , A61B2017/00752 , A61B2017/00969 , A61B2034/105 , A61B2034/2057 , A61B2034/2065 , A61B2090/363 , A61B2090/3937 , G06F19/00 , G06F19/321 , G06K9/00624 , G06K9/481 , G06K9/6202 , G06K9/6267 , G06K9/78 , G06T7/11 , G06T7/246 , G06T7/248 , G06T7/40 , G06T7/74 , G06T2207/20021 , G06T2207/30088 , G06T2207/30196 , G06T2207/30204 , G06T2207/30241 , G06T2207/30242 , G16H30/20 , G16H50/20 , Y10S901/47
摘要： A system and method for tracking, identifying, and labeling objects or features of interest is provided. In some embodiments, tracking is accomplished using unique signature of the feature of interest and image stabilization techniques. According to some aspects a frame of reference using predetermined markers is defined and updated based on a change in location of the markers and/or specific signature information. Individual objects or features within the frame may also be tracked and identified. Objects may be tracked by comparing two still images, determining a change in position of an object between the still images, calculating a movement vector of the object, and using the movement vector to update the location of an image device.
摘要翻译：提供了一种用于跟踪，识别和标注感兴趣的对象或特征的系统和方法。在一些实施例中，使用感兴趣的特征和图像稳定技术的独特签名来实现跟踪。根据一些方面，使用预定标记的参考帧基于标记和/或特定签名信息的位置的变化来定义和更新。框架内的单个对象或特征也可能被跟踪和识别。可以通过比较两个静止图像，确定静止图像之间的对象的位置的变化，计算对象的运动矢量以及使用运动向量来更新图像设备的位置来跟踪对象。

52. 发明授权

US08766982B2 Vectorization of line drawings using global topology and storing in hybrid form 有权
标题翻译：使用全局拓扑和混合形式存储的线图的向量化
公开(公告)号：US08766982B2
公开(公告)日：2014-07-01
申请号：US12843822
申请日：2010-07-26
申请人： Gioacchino Noris , Alexander Hornung , Robert Sumner , Maryann Simmons , Markus Gross
发明人： Gioacchino Noris , Alexander Hornung , Robert Sumner , Maryann Simmons , Markus Gross
IPC分类号： G06T11/20
CPC分类号： G06K9/481 , G06K9/00416
摘要： An animation system can vectorize an image by generating, from an input drawing, a dataset corresponding to vector and digital representations of the input drawing such that a rendering engine could render an image having features in common with the input drawing from the representations, as a collection of strokes and/or objects rather than merely a collection of pixels having pixel color values. A vectorizer might receive an input image, generate a particle clustering data structure from a digitization of the input image, generate a stroke list, wherein strokes in the stroke list correspond to clusters of particles represented in the particle clustering data structure, generate a graph structure that represents connections between strokes on the stroke list, and determine additional characteristics of a stroke beyond the path of the stroke, additional characteristics being stored such that they correspond to strokes. The strokes might be generated using global topology information.
摘要翻译：动画系统可以通过从输入图形生成对应于输入图形的向量和数字表示的数据集来矢量化图像，使得渲染引擎可以从表示形式呈现具有与输入图形共同的特征的图像，作为笔画和/或对象的集合，而不仅仅是具有像素颜色值的像素的集合。向量化器可以接收输入图像，从输入图像的数字化生成粒子聚类数据结构，生成笔画列表，其中笔画列表中的笔画对应于在粒子聚类数据结构中表示的粒子簇，生成图形结构其表示笔划列表上的笔画之间的连接，并且确定笔划的额外特征超出笔画的路径，附加特征被存储使得它们对应于笔画。可以使用全局拓扑信息生成笔画。

53. 发明授权

US08705869B2 Computer-readable storage medium, image recognition apparatus, image recognition system, and image recognition method 有权
标题翻译：计算机可读存储介质，图像识别装置，图像识别系统和图像识别方法
公开(公告)号：US08705869B2
公开(公告)日：2014-04-22
申请号：US13196299
申请日：2011-08-02
申请人： Satoru Osako
发明人： Satoru Osako
IPC分类号： G06K9/46 , G06K9/68
CPC分类号： G06K9/3241 , G06K9/481 , G06K9/6203 , G06K9/6204
摘要： First, it is determined whether or not a contour or vertices have been detected from a certain image. Then, when it is determined that a contour or vertices have been detected from the certain image, a pattern matching process is performed on, in the image, an area surrounded by the contour or the vertices detected from the image. Then, when it is determined that a predetermined object or a predetermined design is displayed in the area, detection position information indicating a position related to the area is stored in a storage area. On the other hand, when it is determined that a contour or vertices have not been detected from the certain image, a pattern matching process is performed on the image on the basis of the detection position information stored in the storage area.
摘要翻译：首先，确定是否从特定图像检测到轮廓或顶点。然后，当确定从特定图像中检测到轮廓或顶点时，在图像中对由图像检测到的轮廓或顶点包围的区域执行模式匹配处理。然后，当确定在该区域中显示预定对象或预定设计时，指示与该区域相关的位置的检测位置信息被存储在存储区域中。另一方面，当确定没有从特定图像中检测到轮廓或顶点时，基于存储在存储区域中的检测位置信息对图像执行图案匹配处理。

54. 发明授权

US08411955B2 Image processing apparatus, image processing method and computer-readable medium 有权
标题翻译：图像处理装置，图像处理方法和计算机可读介质
公开(公告)号：US08411955B2
公开(公告)日：2013-04-02
申请号：US12071257
申请日：2008-02-19
申请人： Shunichi Kimura , Ikken So , Masanori Sekino , Yutaka Koshi
发明人： Shunichi Kimura , Ikken So , Masanori Sekino , Yutaka Koshi
IPC分类号： G06K9/18
CPC分类号： G06K9/6828 , G06K9/481 , G06K2209/01
摘要： An image processing apparatus includes an extracting unit, a representative-image generating unit and a vector converting unit. The extracting unit extracts pixel blocks from image data. The representative-image generating unit generates representative images from the pixel blocks extracted by the extracting unit, based on a similarity between the pixel blocks. The vector converting unit converts the representative images generated by the representative-image generating unit into vector information.
摘要翻译：图像处理装置包括提取单元，代表图像生成单元和向量转换单元。提取单元从图像数据中提取像素块。代表图像生成单元基于像素块之间的相似度从由提取单元提取的像素块生成代表图像。矢量转换单元将由代表图像生成单元生成的代表图像转换为矢量信息。

55. 发明申请

US20130044945A1 METHOD AND SYSTEM FOR DETECTING TEXT IN RASTER IMAGES 有权
标题翻译：用于检测RASTER图像中的文本的方法和系统
公开(公告)号：US20130044945A1
公开(公告)日：2013-02-21
申请号：US13210184
申请日：2011-08-15
申请人： Vyacheslav Nykyforov
发明人： Vyacheslav Nykyforov
IPC分类号： G06K9/00
CPC分类号： G06K9/481 , G06K9/325 , G06K2209/01
摘要： Systems, methods, and applications for detection text in a raster image.
摘要翻译：在光栅图像中检测文本的系统，方法和应用程序。

56. 发明授权

US08363956B1 Method for fast, robust, multi-dimensional pattern recognition 有权
公开(公告)号：US08363956B1
公开(公告)日：2013-01-29
申请号：US11028008
申请日：2004-12-30
申请人： William M. Silver , E. John McGarry , Matthew L. Hill , Nigel J. Foster , Sanjay Nichani , Willard P. Foster , Adam Wagman
发明人： William M. Silver , E. John McGarry , Matthew L. Hill , Nigel J. Foster , Sanjay Nichani , Willard P. Foster , Adam Wagman
IPC分类号： G06K9/62
CPC分类号： G06K9/6201 , G06K9/481 , G06K9/6204
摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.

57. 发明授权

US08340446B2 Apparatus and method for generating chain code 有权
标题翻译：用于生成链码的装置和方法
公开(公告)号：US08340446B2
公开(公告)日：2012-12-25
申请号：US12036015
申请日：2008-02-22
申请人： Jae-Wook Jeon , Dong-Kyun Kim , Jung-Uk Cho , Seung-Hun Jin , Dae-Ro Lee , Jong-Hyun Park , Ki-Hoon Kim , Thien-Cong Pham
发明人： Jae-Wook Jeon , Dong-Kyun Kim , Jung-Uk Cho , Seung-Hun Jin , Dae-Ro Lee , Jong-Hyun Park , Ki-Hoon Kim , Thien-Cong Pham
IPC分类号： G06K9/48
CPC分类号： G06K9/481 , G06T9/20
摘要： Disclosed are a chain code generating apparatus and a method thereof. In accordance with an embodiment of the present invention, the chain code generating apparatus can include an image input unit, receiving an image signal from a camera and converting the received image signal to a digital image signal, and separating a synchronizing signal from the digital image signal and outputting the synchronizing signal; an image storing unit, storing image data corresponding to an active image section of the digital image signal in units of frame based on the synchronizing signal; and a code generating unit, reading the image data stored in the image storing unit and performing an outline search of the analysis portion, and generating a chain code according to a correlation between adjacent pixels forming an outline of the analysis portion in accordance with the searched result.
摘要翻译：公开了一种链码生成装置及其方法。根据本发明的实施例，链码生成装置可以包括图像输入单元，从相机接收图像信号并将接收的图像信号转换为数字图像信号，并且从数字图像分离同步信号信号并输出同步信号; 图像存储单元，基于同步信号以帧为单位存储与数字图像信号的有效图像部分对应的图像数据; 代码生成单元，读取存储在图像存储单元中的图像数据，并执行分析部分的轮廓搜索，并且根据搜索到的分析部分的轮廓的相邻像素之间的相关性生成链码结果。

58. 发明授权

US08270722B2 Image processing with preferential vectorization of character and graphic regions 有权
标题翻译：图像处理与特征和图形区域的优化向量化
公开(公告)号：US08270722B2
公开(公告)日：2012-09-18
申请号：US12702810
申请日：2010-02-09
申请人： Naoki Ito , Tomotoshi Kanatsu , Taeko Yamazaki
发明人： Naoki Ito , Tomotoshi Kanatsu , Taeko Yamazaki
IPC分类号： G06K9/46 , G06K9/34 , G06K9/00
CPC分类号： G06K9/481 , G06K2209/01
摘要： Image processing by which both of high compressibility and high image quality are achieved, and in which characters in character regions and graphics in graphic regions are vectorized. If a pixel of a character in a character region overlaps with a graphic in a graphic region, graphic region vectorization is performed first, whereas if a pixel of a character in the character region does not overlap with a graphic in the graphic region, character region vectorization is performed first.
摘要翻译：实现了高压缩性和高图像质量两者的图像处理，并且其中图形区域中的字符区域和图形中的字符被矢量化。如果字符区域中的字符的像素与图形区域中的图形重叠，则首先执行图形区域矢量化，而如果字符区域中的字符的像素与图形区域中的图形不重叠，则字符区域首先执行矢量化。

59. 发明授权

US08249362B1 Method for fast, robust, multi-dimensional pattern recognition 有权
标题翻译：快速，健壮，多维模式识别的方法
公开(公告)号：US08249362B1
公开(公告)日：2012-08-21
申请号：US11028076
申请日：2004-12-31
申请人： William M. Silver , E. John McGarry
发明人： William M. Silver , E. John McGarry
IPC分类号： G06K9/62
CPC分类号： G06K9/6201 , G06K9/481 , G06K9/6204
摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurali of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.
摘要翻译：公开了一种用于确定图像中的预定图案的一个或多个实例的不存在或不存在以及用于在多维空间内确定每个找到的实例的位置的方法。模型代表要发现的模式，该模型包括多个探针。每个探针表示在给定姿势下在图像中进行测试的相对位置，每个这样的测试提供了该模式存在于姿势的证据。该方法还包括在多个姿势中的每一个处的模型与运行时图像的比较。在每个姿态计算匹配得分以提供匹配得分表面。然后，匹配得分与接受阈值进行比较，并用于提供图像中图案的任何实例的位置。

60. 发明授权

US08244041B1 Method for fast, robust, multi-dimensional pattern recognition 有权
标题翻译：快速，健壮，多维模式识别的方法
公开(公告)号：US08244041B1
公开(公告)日：2012-08-14
申请号：US11029104
申请日：2004-12-31
申请人： William M. Silver , E. John McGarry , Nigel J. Foster , Sanjay Nichani
发明人： William M. Silver , E. John McGarry , Nigel J. Foster , Sanjay Nichani
IPC分类号： G06K9/62
CPC分类号： G06K9/6201 , G06K9/481 , G06K9/6204
摘要： Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.
摘要翻译：公开了一种用于确定图像中的预定图案的一个或多个实例的不存在或不存在以及用于在多维空间内确定每个找到的实例的位置的方法。模型代表要发现的模式，该模型包括多个探针。每个探针表示在给定姿势下在图像中进行测试的相对位置，每个这样的测试提供了该模式存在于姿势的证据。该方法还包括在多个姿势中的每个姿势下的模型与运行时图像的比较。在每个姿态计算匹配得分以提供匹配得分表面。然后，匹配得分与接受阈值进行比较，并用于提供图像中图案的任何实例的位置。

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