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. 发明专利

ES2875919T3 Programa de búsqueda de imagen de caso similar, dispositivo de búsqueda de imagen de caso similar y método de búsqueda de imagen de caso similar 未知
公开(公告)号：ES2875919T3
公开(公告)日：2021-11-11
申请号：ES18763395
申请日：2018-01-24
申请人： FUJITSU LTD
发明人： MORIWAKI YASUTAKA , SUGIMURA MASAHIKO , ENDO SUSUMU , TAKEBE HIROAKI , BABA TAKAYUKI , UEHARA YUSUKE
IPC分类号： A61B6/03 , A61B6/00 , G06F16/00 , G06F16/53 , G06F16/532 , G06F16/583 , G06K9/62 , G06T1/00 , G06T7/00 , G06T7/10 , G06T7/11 , G06T7/12 , G16H30/00 , G16H50/70
摘要： Programa de búsqueda de imagen de caso similar que hace que un ordenador ejecute un procedimiento, que comprende: extraer un área de campo pulmonar a partir de una imagen médica e identificar (S1405) un contorno del área de campo pulmonar que incluye una pared torácica y un mediastino; identificar una posición en la que se dividen internamente la pared torácica y el mediastino y dividir el área de campo pulmonar en un área central y un área periférica basándose en la forma del área de campo pulmonar; contar (S1406) el número de píxeles que indican lesiones en cada una del área central y el área periférica divididas; e identificar una imagen de caso similar correspondiente a un nivel de similitud del número contado de píxeles que indican lesiones haciendo referencia a una unidad de almacenamiento que almacena el número de píxeles que indican lesiones en cada una de las áreas.

2. 发明专利

JP2014110582A Video editing device and video editing method, and video editing program 有权
标题翻译：视频编辑设备和视频编辑方法以及视频编辑程序
公开(公告)号：JP2014110582A
公开(公告)日：2014-06-12
申请号：JP2012264986
申请日：2012-12-04
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ISHIHARA MASAKI , NAKAMURA SHUGO , SUGIMURA MASAHIKO , ENDO SUSUMU , BABA TAKAYUKI , UEHARA YUSUKE
IPC分类号： H04N5/91 , G06T3/00 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To generate a summary video for collectively reproducing attributes and movement paths of a plurality of objects.SOLUTION: The present invention comprises: a specification unit for receiving a plurality of videos showing a movement path of each object at a prescribed location as background and specifying an object region including an image of each object in each image included in each video; a detection unit for detecting a portion in which object regions corresponding to respective objects overlap each other in each image in a summary video generated by superposing images having the same relative time from the beginning of each video one on another; a calculation unit for calculating a reduction rate for making the overlapping portion smaller by scaling down relative to a vertex farthest from the overlapping portion in each object region; and an adjustment unit for adjusting the positions of object regions so that the center of gravity position of each object region shrunk by the reduction rate obtained by calculation is brought closer to the center of the gravity position of each object region before being shrunk.
摘要翻译：要解决的问题：产生用于集体再现多个对象的属性和移动路径的摘要视频。解决方案：本发明包括：一个指定单元，用于接收多个视频，其显示每个对象在规定位置的移动路径作为背景并且指定包括每个视频中包括的每个图像中的每个对象的图像的对象区域; 检测单元，用于检测在通过将具有与每个视频开始相同的相对时间的图像叠加在另一个上的图像中生成的概要视频中，检测其中对应于各个对象的对象区域彼此重叠的部分; 计算单元，用于计算用于使所述重叠部分相对于在每个对象区域中与所述重叠部分最远的顶点缩小而缩小的缩小率; 以及调整单元，用于调整对象区域的位置，使得通过计算获得的缩小率缩小的每个对象区域的重心位置在收缩之前更靠近每个对象区域的重心位置的中心。

3. 发明专利

JP2013012105A Object recognition support device, program, and method 有权
标题翻译：对象识别支持设备，程序和方法
公开(公告)号：JP2013012105A
公开(公告)日：2013-01-17
申请号：JP2011145151
申请日：2011-06-30
申请人： Fujitsu Ltd , 富士通株式会社
发明人： NAKAMURA SHUGO , ISHIHARA MASAKI , BABA TAKAYUKI , SUGIMURA MASAHIKO , ENDO SUSUMU , UEHARA YUSUKE , MASUMOTO DAIKI , OSADA SHIGEMI
IPC分类号： G06T7/00
摘要： PROBLEM TO BE SOLVED: To provide an object recognition support device for determining image amount adequate for object recognition.SOLUTION: An object recognition support device 1 includes: a first feature extraction unit 11 for extracting a feature of an acquired image; a first feature recording unit 12 for recording the feature; a dispersion calculation unit 13 for calculating dispersion of a feature group recorded in the first feature recording unit 12; a dispersion recording unit 14 for recording the dispersion; and a convergence determination unit 15 for determining whether the dispersion is converged on the basis of a progress of the dispersion recorded in the dispersion recording unit 14 and, when the dispersion is converged, making a notification of the acquisition completion of the image. The object recognition support device 1 supports an object recognition device 3 to perform object recognition with the adequate number of images.
摘要翻译：要解决的问题：提供一种用于确定足以进行对象识别的图像量的对象识别支持装置。对象识别支持装置1包括：第一特征提取单元11，用于提取所获取的图像的特征; 用于记录特征的第一特征记录单元12; 用于计算记录在第一特征记录单元12中的特征组的色散的色散计算单元13; 用于记录色散的色散记录单元14; 以及收敛确定单元15，用于基于记录在色散记录单元14中的色散的进展来确定色散是否收敛，并且当色散被收敛时，进行图像的拍摄完成的通知。对象识别支持装置1支持对象识别装置3，以适当数量的图像进行对象识别。版权所有（C）2013，JPO＆INPIT

4. 发明专利

JP2003178333A IMAGE GENERATION DEVICE AND METHOD, AND STORAGE MEDIUM 审中-公开
公开(公告)号：JP2003178333A
公开(公告)日：2003-06-27
申请号：JP2002311927
申请日：2002-10-25
申请人： FUJITSU LTD
发明人： ARAI MASATOSHI , SUGIMURA MASAHIKO , MURAKAMI KOICHI
IPC分类号： G06T17/40
摘要： PROBLEM TO BE SOLVED: To generate various images for expressing various objects in a two-dimensional plane in the state further matched to reality by solving the unnaturalness by use of existing image data. SOLUTION: According to a display instruction from a display command part 11 such as the brightening of the emitter of a character, a display part 14 reads the image data of beam stored in a data storage part 12 (S12), and reads image data of background (S13). The display part 14 reads luminance information for two or more gradations in the beam light from a spot light source stored in a luminance information storage part 13 (S14). An image of the state where the background is illuminated with the light beam is generated and displayed (S15) with mixture of colors of the light beam and the background. COPYRIGHT: (C)2003,JPO

5. 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。

6. 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。

7. 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。

8. 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。

9. 发明专利

JP2013012163A Image recognition device, image recognition method and computer program for image recognition 有权
标题翻译：图像识别装置，图像识别方法和用于图像识别的计算机程序
公开(公告)号：JP2013012163A
公开(公告)日：2013-01-17
申请号：JP2011146077
申请日：2011-06-30
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 , OSADA SHIGEMI , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： G06T7/00
CPC分类号： G06K9/00711 , G06K9/00677
摘要： PROBLEM TO BE SOLVED: To provide an image recognition device in which recognition accuracy of an object reflected on a moving picture is raised.SOLUTION: An image recognition device has: a section setting part (21) which sets a first section in a moving picture; a first object detection part (22) which recognizes an object which is reflected on at least one picture included in the first section by using a general-purpose object identifier which uses a plurality of objects belonging to a predetermined category as recognition objects; a selection part (23) which selects a subcategory which the object reflected on the moving picture is estimated to belong to, from among a plurality of subcategories including a part of objects belonging to the predetermined category based on the objects recognized for the first section; and a second object detection part (26) which recognizes the object which is reflected on at least one picture included in a second section except the first section in the moving picture by using an individual object identifier which uses only the objects belonging to the selected subcategory as recognition objects.
摘要翻译：要解决的问题：提供一种图像识别装置，其中反映在运动图像上的对象的识别精度提高。解决方案：图像识别装置具有：设置运动图像中的第一部分的部分设置部分（21）; 第一对象检测部（22），其通过使用使用属于预定类别的多个对象的通用对象标识符来识别在包括在第一部分中的至少一个图片上被反射的对象的对象; 基于对于第一部分识别的对象，从包括属于预定类别的对象的一部分的多个子类别中，选择选择反映在运动图像上的对象的子类别的选择部分（23）以及第二对象检测部（26），其通过使用仅使用属于所选子类别的对象的单独对象标识符来识别被包含在除了运动图像中的第一部分之外的第二部分中的至少一个图片上被反射的对象作为识别对象。版权所有（C）2013，JPO＆INPIT

10. 发明专利

JP2012216089A Support device, support program, and support method 有权
标题翻译：支持设备，支持程序和支持方法
公开(公告)号：JP2012216089A
公开(公告)日：2012-11-08
申请号：JP2011081132
申请日：2011-03-31
申请人： Fujitsu Ltd , 富士通株式会社
发明人： SUGIMURA MASAHIKO , NAKAMURA SHUGO , ISHIHARA MASAKI , BABA TAKAYUKI , ENDO SUSUMU , UEHARA YUSUKE , MASUMOTO DAIKI , OSADA SHIGEMI
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To accurately determine user's current knowledge about a word.SOLUTION: A support device 10 specifies: a retrieval purpose of retrieving a retrieved word, based on the retrieved word and retrieval time for retrieving the retrieved word that are included in a first DB 13a, and also based on document use time and use attribute that are included in a second DB 13b; a use purpose of the retrieved word, based on a rate of use attribute of a document group that is used at the retrieval time for retrieving the retrieved word; and each state of current knowledge relating to the retrieved word and state of desired knowledge relating thereto, based on the retrieval purpose, the use purpose, and a fourth DB 13d. The fourth DB 13d includes the state of the current knowledge relating to a retrieval word and the state of the desired knowledge relating thereto by association with each other in accordance with the retrieval purpose of the retrieved word and the use purpose thereof. The support device 10 stores the retrieved word and the state of the current knowledge relating to the specified retrieved word and the state of the desired knowledge relating to the retrieved word in a third DB 13c by association with each other.
摘要翻译：要解决的问题：准确地确定用户当前对某个单词的了解。解决方案：支持设备10指定：基于检索到的字检索检索到的单词的检索目的，以及用于检索包括在第一DB 13a中的检索到的单词的检索时间，以及基于文档使用时间和使用属性包含在第二个DB 13b中; 基于在检索时间用于检索检索到的单词的文档组的使用率属性的检索词的使用目的; 以及基于检索目的，使用目的和第四DB 13d，与检索到的与所述知识相关的知识的状态和状态相关的当前知识的每个状态。第四DB 13d根据检索词的检索目的及其使用目的，通过相关联地包括与检索词相关的当前知识的状态和与之相关的期望知识的状态。支持装置10将检索到的单词和与指定的检索词相关的当前知识的状态和与检索到的单词相关的期望知识的状态彼此关联地存储在第三DB 13c中。版权所有（C）2013，JPO＆INPIT

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