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. 发明专利

JP2007080188A Drawing retrieval program, method and apparatus 有权
标题翻译：绘图检索程序，方法和设备
公开(公告)号：JP2007080188A
公开(公告)日：2007-03-29
申请号：JP2005270427
申请日：2005-09-16
申请人： Fujitsu Ltd , 富士通株式会社
发明人： UEHARA YUSUKE , BABA TAKAYUKI , ENDO SUSUMU , SHIITANI SHUICHI , MASUMOTO DAIKI , OSADA SHIGEMI
IPC分类号： G06F17/50
摘要： PROBLEM TO BE SOLVED: To improve efficiency in work where a user retrieves a drawing, by easily reading contents of the drawing when the drawing simplified in accordance with the reduction ratio of the drawing is displayed and the user browses the drawing.
SOLUTION: A drawing retrieval apparatus includes: a priority table storage section where drawing elements constituting a drawing is associated with priority of display for each drawing element; an area complexity computation section for computing an area complexity representing the degree of complexity of the drawing elements in divided areas obtained by dividing said drawing; a display complexity computation section for computing a display complexity representing the degree of complexity in the display of drawing elements in said divided areas; a threshold value computation section for computing a threshold value determining whether to display the drawing elements from the computed display complexity; and a simplified drawing creation section for creating a simplified drawing by excluding drawing elements having the priority lower than the computed threshold value.
COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：为了提高用户检索图纸的工作效率，通过显示根据图纸的缩小比简化的绘图，并且用户浏览图形，通过容易地读取图形的内容。解决方案：绘图检索装置包括：优先级表存储部分，其中构成图形的绘图元素与每个绘图元素的显示优先级相关联; 区域复杂度计算部分，用于计算表示通过划分所述图形而获得的分割区域中的绘制元素的复杂程度的区域复杂度; 显示复杂度计算部分，用于计算表示所述分割区域中的绘图元素的显示的复杂程度的显示复杂度; 阈值计算部分，用于计算从所计算的显示复杂度中确定是否显示绘图元素的阈值; 以及简化绘图创建部分，用于通过排除具有低于计算出的阈值的优先级的绘图元素来创建简化的绘图。版权所有（C）2007，JPO＆INPIT

52. 发明专利

JP2005228131A Drawing verification device 有权
标题翻译：绘图验证装置
公开(公告)号：JP2005228131A
公开(公告)日：2005-08-25
申请号：JP2004037061
申请日：2004-02-13
申请人： Fujitsu Ltd , 富士通株式会社
发明人： LIU RUJIE , BABA TAKAYUKI , ENDO SUSUMU , SHIITANI SHUICHI , UEHARA YUSUKE , MASUMOTO DAIKI
IPC分类号： G06F17/50 , G06F15/80 , G06F17/30 , G06K9/48 , G06K9/68 , G06T1/00 , G06T7/60 , G09G5/00
CPC分类号： G06K9/469 , G06F17/30259 , G06K9/4638 , Y10S707/99933 , Y10S707/99937
摘要： PROBLEM TO BE SOLVED: To provide a drawing verification device which directly collates shapes included in drawings to output a retrieval result of the drawing.
SOLUTION: After making the lines of an inputted image (drawing) finer, a primitive is extracted. On this occasion, a coarse primitive is extracted first, then by merge processing based on greedy strategy, the coarse primitive becomes the primitive. From the primitive and spatial relation thereof, an attribute graph describing the contents and structure of the drawing is generated. The attribute graph is generated by using a deformed Delaunay triangle and an attribute set. The attribute graph having the attribute set is generated both for an inquiry drawing and a verification drawing, and drawing verification is performed by verification of these drawings.
COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：提供一种图形验证装置，其直接对照图中包含的形状以输出图形的检索结果。
解决方案：使输入图像（绘图）的线条更细，提取原语。在这种情况下，首先提取粗略的原语，然后通过基于贪心策略的合并处理，粗略原语成为原语。从原始和空间关系，生成描述图的内容和结构的属性图。属性图是通过使用变形的Delaunay三角形和属性集来生成的。产生具有属性集的属性图用于查询图和验证图，并且通过验证这些图来执行绘图验证。版权所有（C）2005，JPO＆NCIPI

53. 发明专利

JP2004164331A Image retrieval method, image retrieval device and image retrieval program 审中-公开
公开(公告)号：JP2004164331A
公开(公告)日：2004-06-10
申请号：JP2002329965
申请日：2002-11-13
申请人： Fujitsu Ltd , 富士通株式会社
发明人： MASUMOTO DAIKI , ENDO SUSUMU , UEHARA YUSUKE , SHIITANI SHUICHI , BABA TAKAYUKI
IPC分类号： G06T1/00 , G06F17/30 , G06T17/40
摘要： PROBLEM TO BE SOLVED: To efficiently retrieve information which a user desires from large quantities of image data.
SOLUTION: This image retrieval program decides an image group of a retrieval target on the basis of retrieval conditions inputted by the user, converts an image of the retrieval target into an icon visually representing the image of the retrieval target, extracts a feature quantity for deciding a position on a display screen where the icon or the image of the retrieval target is disposed, from image information about an original image, decides a sheet on the display screen and a position in the sheet where the icon or the image of the retrieval target is disposed, on the basis of the feature quantity, and overlappingly arranges the sheet wherein the icons or the images of the retrieval targets are arranged side by side according to the feature quantities of the images, inside a virtual three-dimensional space. Thereby, the information which the user desires can be efficiently retrieved from large quantities of the image data.
COPYRIGHT: (C)2004,JPO

54. 发明专利

JP2014110050A Method for determining integrated space in three-dimensional model, equipment and image processing system 有权
标题翻译：用于确定三维模型，设备和图像处理系统中的集成空间的方法
公开(公告)号：JP2014110050A
公开(公告)日：2014-06-12
申请号：JP2013244713
申请日：2013-11-27
申请人： Fujitsu Ltd , 富士通株式会社
发明人： WONG YUEN-HON , LIU RUJIE , ENDO SUSUMU , BABA TAKAYUKI , UEHARA YUSUKE
IPC分类号： G06F17/50
摘要： PROBLEM TO BE SOLVED: To provide a method for determining integrated space in a three-dimensional model, equipment and an image processing system.SOLUTION: This method includes a first entity set recognition step for recognizing a first entity set having a common plane common to a concave space in a three-dimensional model and including the concave space for each concave space in the three-dimensional model; a second entity set recognition step for recognizing a second entity set not having a common plane common to the concave space in the three-dimensional model but including the concave space for each concave space; and an integrated space determination step for determining entities in the first entity set and the second entity set and the concave space as an integrated space.
摘要翻译：要解决的问题：提供一种用于确定三维模型，设备和图像处理系统中的集成空间的方法。解决方案：该方法包括：第一实体集合识别步骤，用于识别具有共同平面的共同平面的第一实体集合三维模型中的凹陷空间，并且在三维模型中包括每个凹陷空间的凹入空间; 第二实体集识别步骤，用于识别在三维模型中不具有与所述凹空间共同的共同平面的第二实体集合，但是包括每个凹入空间的所述凹入空间; 以及集成空间确定步骤，用于将第一实体集合中的实体和第二实体集合以及凹空间确定为集成空间。

55. 发明专利

JP2014063494A Classification device, classification method, and electronic facility 有权
标题翻译：分类设备，分类方法和电子设备
公开(公告)号：JP2014063494A
公开(公告)日：2014-04-10
申请号：JP2013193252
申请日：2013-09-18
申请人： Fujitsu Ltd , 富士通株式会社
发明人： YI BI , LIU RUJIE , SUGIMURA MASAHIKO , BABA TAKAYUKI , UEHARA YUSUKE
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To provide a classification device capable of solving the problem that a kind value of a measurement sample obtained by the conventional learning method by means of an image is not accurate, a classification method, and an electronic facility.SOLUTION: The classification device of this invention includes a classification unit for classifying a target sample, a determination unit for respectively determining training samples correlating to each aggregation of the target sample, a deletion unit for deleting a kind value of the training sample whose kind value is not accurate, and a calculation unit for acquiring, with regarding the target sample as a measurement sample, the kind value of the measurement sample according to similarity between each measurement sample and each training sample, and similarity between two measurement samples. The classification method executes each step for achieving a function of the classification device. The electronic facility includes the classification device. A technology of this invention is applied to an information processing area.
摘要翻译：要解决的问题：提供一种能够解决通过图像通过常规学习方法获得的测量样本的种类值不准确的问题的分类装置，分类方法和电子设备。解决方案：本发明的分类装置包括：分类单元，用于对目标样本进行分类;确定单元，用于分别确定与目标样本的每个聚合相关的训练样本;删除单元，用于删除种类值不准确的训练样本的种类值以及计算单元，用于根据每个测量样本和每个训练样本之间的相似度以及两个测量样本之间的相似度来获取关于作为测量样本的目标样本的测量样本的种类值。分类方法执行用于实现分类装置的功能的每个步骤。电子设备包括分类装置。本发明的技术应用于信息处理领域。

56. 发明专利

JP2013242609A Program, image processing apparatus, and image processing method 有权
标题翻译：程序，图像处理装置和图像处理方法
公开(公告)号：JP2013242609A
公开(公告)日：2013-12-05
申请号：JP2012113646
申请日：2012-05-17
申请人： Fujitsu Ltd , 富士通株式会社
发明人： BABA TAKAYUKI , NAKAMURA SHUGO , ISHIHARA MASAKI , SUGIMURA MASAHIKO , ENDO SUSUMU , UEHARA YUSUKE , MASUMOTO DAIKI , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： G06T7/00
CPC分类号： G06K9/46 , G06K9/469 , G06K9/6892
摘要： PROBLEM TO BE SOLVED: To improve efficiency in searching similar areas in supporting creation of an image corpus.SOLUTION: A program includes the steps of: acquiring an area designated in an object image, and an attribute given to the area; searching a pattern corresponding to the given attribute, the pattern being similar to patterns created from a predetermined numbers of areas having the same attribute, from storage means for storing patterns created from areas of a plurality of areas in an image having the same given attribute in association with the attribute; and causing a computer to perform processing to search an area similar to the predetermined number of areas on the basis of the searched pattern.
摘要翻译：要解决的问题：提高在支持图像语料库的创建中搜索类似区域的效率。解决方案：程序包括以下步骤：获取对象图像中指定的区域和给予该区域的属性; 搜索与所述给定属性相对应的模式，所述模式类似于从具有相同属性的预定数量的区域创建的图案，所述存储装置用于存储从具有相同给定属性的图像中的多个区域的区域创建的图案与属性关联; 并且使得计算机执行基于搜索到的图案来搜索类似于预定数量的区域的区域的处理。

57. 发明专利

JP2013206470A Image labeling method and device 有权
标题翻译：图像标签方法和设备
公开(公告)号：JP2013206470A
公开(公告)日：2013-10-07
申请号：JP2013064274
申请日：2013-03-26
申请人： Fujitsu Ltd , 富士通株式会社
发明人： LIU RUJIE , NAKAMURA SHUGO , UEHARA YUSUKE
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To provide an image labeling method and device.SOLUTION: The image labeling method relating to this invention includes: a step for selecting a plurality of other images similar to an image in image features among a prescribed image collection about each image in the image collection; a step for acquiring a plurality of fitting coefficients of the image by using the image features of the plurality of other images to fit the image features of the image; and a step for generating a label of the image by using labels of the plurality of other images on the basis of the plurality of fitting coefficients of the image.
摘要翻译：要解决的问题：提供一种图像标记方法和装置。解决方案：本发明的图像标记方法包括：在关于每个图像的规定图像集合中选择类似于图像特征中的图像的多个其他图像的步骤在图像集合中; 通过使用多个其他图像的图像特征来获取图像的多个拟合系数以适合图像的图像特征的步骤; 以及基于图像的多个拟合系数，通过使用多个其他图像的标签来生成图像的标签的步骤。

58. 发明专利

JP2013196029A Device, method, and program for interpolating traffic line of moving object 有权
标题翻译：用于插入移动对象的交通线的设备，方法和程序
公开(公告)号：JP2013196029A
公开(公告)日：2013-09-30
申请号：JP2012059178
申请日：2012-03-15
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ISHIHARA MASAKI , NAKAMURA SHUGO , BABA TAKAYUKI , SUGIMURA MASAHIKO , ENDO SUSUMU , UEHARA YUSUKE , MASUMOTO DAIKI
IPC分类号： G06T7/20 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To achieve accurate interpolation of a traffic line even in the case that a movement direction of a moving object is changed in a section where the traffic line of the moving object is lost.SOLUTION: Traffic line data of moving objects extracted from a moving image is generated, and appearance frequencies of the moving objects in a plurality of areas into which the image is divided are calculated from past traffic line data, and weights of a plurality of second moving objects are calculated from the position of the end of an incomplete traffic line and a movement direction of a first moving object at the end, and image similarities between images of the first moving object and the plurality of second moving objects are calculated respectively, and an evaluation value of each of the plurality of second moving objects is calculated by an evaluation function which includes the appearance frequency, weight, and image similarity of the second moving object as parameters and is set so that the influence of the appearance frequency is larger for larger variation in a movement direction of the second moving object and the influence of the image similarity is larger for smaller variation in the movement direction of the second moving object, and the incomplete traffic line is interpolated on the basis of the evaluation values.
摘要翻译：要解决的问题：即使在移动物体的行驶路线丢失的部分中移动物体的移动方向变化的情况下也能够实现交通线路的精确插值。解决方案：提取的移动物体的交通线路数据从运动图像生成，并且从过去的交通线路数据计算分割图像的多个区域中的运动物体的出现频率，并且从终点的位置计算多个第二移动物体的权重不完整的交通线路和第一移动物体的移动方向在结束时分别计算，并且分别计算第一移动物体和多个第二移动物体的图像之间的图像相似度，并且分别计算多个第二移动物体的评估值通过包含第二移动物体的出现频率，权重和图像相似度的评价函数作为参数来计算移动物体并且被设置为使得对于第二移动物体的移动方向上的较大变化，出现频率的影响较大，并且对于第二移动物体的移动方向的较小变化，图像相似度的影响较大，基于评估值对不完整的交通线进行内插。

59. 发明专利

JP2013175185A Space recognition method and device of three-dimensional model, and image processing system 有权
标题翻译：空间识别方法和三维模型的设备和图像处理系统
公开(公告)号：JP2013175185A
公开(公告)日：2013-09-05
申请号：JP2013033483
申请日：2013-02-22
申请人： Fujitsu Ltd , 富士通株式会社
发明人： WONG YUEN-HON , LIU RUJIE , ENDO SUSUMU , UEHARA YUSUKE
IPC分类号： G06T19/00 , G06T17/00
摘要： PROBLEM TO BE SOLVED: To provide a method and device for recognizing space in a three-dimensional model, and further to provide an image processing system including the device.SOLUTION: A space recognition method of a three-dimensional model includes the steps of: classifying vertices of the three-dimensional model so that the vertices connected each other through a contour line of the three-dimensional model are classified into the same group; deciding a convex hull of the vertex included in a reference plane which is a plane in the three dimensional model including vertices belonging different groups; and recognizing a space determined by a group satisfying conditions that (a) the group does not include any vertex in the convex hull, and (b) in the group, the vertex connected to the reference plane through the contour line is located inside the three dimensional model with respect to the reference plane.
摘要翻译：要解决的问题：提供一种用于识别三维模型中的空间的方法和装置，并且还提供包括该装置的图像处理系统。解决方案：三维模型的空间识别方法包括以下步骤：对三维模型的顶点进行分类，使得通过三维模型的轮廓线相互连接的顶点分为同一组; 确定包括在参考平面中的顶点的凸包，该参考平面是包括属于不同组的顶点的三维模型中的平面; 并且识别由满足以下条件的组所确定的空间：（a）所述组不包括所述凸包中的任何顶点，以及（b）在所述组中，通过所述轮廓线连接到所述参考平面的顶点位于所述三维相对于参考平面的三维模型。

60. 发明专利

JP2013152543A Image storage program, method and device 审中-公开
标题翻译：图像存储程序，方法和设备
公开(公告)号：JP2013152543A
公开(公告)日：2013-08-08
申请号：JP2012012246
申请日：2012-01-24
申请人： Fujitsu Ltd , 富士通株式会社
发明人： BABA TAKAYUKI , NAKAMURA SHUGO , ISHIHARA MASAKI , SUGIMURA MASAHIKO , ENDO SUSUMU , UEHARA YUSUKE , MASUMOTO DAIKI , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： G06F17/30 , G06T1/00
CPC分类号： G06K9/6267 , G06F17/30256 , G06T11/60
摘要： PROBLEM TO BE SOLVED: To more efficiently improve work for imparting character information corresponding to characteristics of an image to the image as meta data, and to store the image to which the meta data corresponding to the characteristics of the image has been imparted.SOLUTION: The image storage program executes processing of: specifying to a computer a second image similar to a first image associated with the character information; causing a display device to display the second image in an identifiable manner; further causing the display device to display the character information; receiving instruction information instructing adoption of the character information for the second image; and, based on the instruction information, storing image information on the second image and the character information in association with each other in a storage device.
摘要翻译：要解决的问题：为了更有效地改进将与图像的特征相对应的字符信息作为元数据进行工作，并且存储与图像的特性对应的元数据已被赋予的图像。解决方案：图像存储程序执行以下处理：向计算机指定与与字符信息相关联的第一图像类似的第二图像; 使显示装置以可识别的方式显示第二图像; 进一步使显示装置显示字符信息; 接收指示采用第二图像的字符信息的指令信息; 并且基于指示信息，在存储装置中相互关联地存储关于第二图像的图像信息和字符信息。

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