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

JP2015029504A コロニーカウント装置、コロニーカウント方法、およびコロニーカウントプログラム有权
标题翻译： COLONY COUNT DEVICE，COLONY COUNT METHOD，AND COLONY COUNT PROGRAM
公开(公告)号：JP2015029504A
公开(公告)日：2015-02-16
申请号：JP2013163602
申请日：2013-08-06
申请人：富士通株式会社 , Fujitsu Ltd
发明人： ENDO SUSUMU , ISHIHARA MASAKI , SUGIMURA MASAHIKO , BABA TAKAYUKI , UEHARA YUSUKE , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： C12M1/34 , G01N21/17 , G06M11/00
摘要：【課題】簡易にコロニーをカウントすることができるコロニーカウント装置、コロニーカウント方法、およびコロニーカウントプログラムを提供する。【解決手段】コロニーカウント装置は、培養された菌の画像を取得する画像取得部と、前記菌の画像において、輝度ピークを検出するピーク検出部と、前記ピーク検出部が検出した輝度ピークの数に基づいてコロニーをカウントするカウント部と、を備える。【選択図】図3
摘要翻译：要解决的问题：提供一种可以简单地计数菌落的菌落计数装置，菌落计数方法和菌落计数程序。解决方案：菌落计数装置包括获取培养细菌的图像的图像获取单元，峰值检测检测细菌图像中的亮度峰值的单元，以及基于由峰值检测单元检测出的亮度峰数来计数菌落的计数部。

2. 发明专利

JP2013152607A Management program and device 有权
标题翻译：管理程序和设备
公开(公告)号：JP2013152607A
公开(公告)日：2013-08-08
申请号：JP2012013018
申请日：2012-01-25
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ENDO SUSUMU , NAKAMURA SHUGO , ISHIHARA MASAKI , BABA TAKAYUKI , SUGIMURA MASAHIKO , UEHARA YUSUKE , MASUMOTO DAIKI , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： G06F17/30
CPC分类号： G06F17/30274 , G06F17/30247
摘要： PROBLEM TO BE SOLVED: To specify a kind in which a feature of an image should be preferentially learned, from among kinds in which a feature of an image is unlearnt.SOLUTION: An image management system retrieves an image corresponding to a first kind designated by a retrieval request received from a terminal device, and an image corresponding to a second kind relating to the first kind, from an image DB storing a plurality of images in association with at least a part of a plurality of kinds, respectively. A management program allows a computer that manages the image management system to execute a method including: referring to a learning state storage unit for storing a learning state showing whether or not a feature amount relating to a feature of the image associated with each kind has been calculated, for each of the plurality of kinds; retrieving the unlearnt kind in which the feature amount has not been calculated, from among the plurality of kinds; specifying a relevant kind relating to the unlearnt kind; and executing processing for outputting the unlearnt kind specified as a calculation candidate of the feature quantity according to a learning state of the relevant kind.
摘要翻译：要解决的问题：从图像的特征不清楚的种类中，指定要优先学习图像的特征的种类。解决方案：图像管理系统检索对应于由图像指定的第一种类型的图像分别从与终端装置接收的检索请求和与第一种相关的第二类型的图像从存储多个图像的图像DB分别与至少一部分相关联。管理程序允许管理图像管理系统的计算机执行一种方法，包括：参考学习状态存储单元，用于存储学习状态，该学习状态表示与每种类型相关联的图像的特征相关的特征量是否已被对于多种类型中的每一种计算; 从多种中检索未计算特征量的不确定种类; 具体说明有关种类的有关种类; 以及根据相关种类的学习状态执行用于输出被指定为特征量的计算候选的不明种类的处理。

3. 发明专利

JP2013097645A Recognition support device, recognition support method and program 有权
标题翻译：识别支持设备，识别支持方法和程序
公开(公告)号：JP2013097645A
公开(公告)日：2013-05-20
申请号：JP2011240877
申请日：2011-11-02
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 , NAITO HIROHISA , MIYAZAKI AKIRA
IPC分类号： G06T7/00
摘要： PROBLEM TO BE SOLVED: To provide a recognition support device, a recognition support method and a program for performing appropriate object recognition in a short time by appropriately photographing an image which is subject to object recognition.SOLUTION: In the recognition support device for supporting an object recognition device to perform object recognition, an image acquisition section acquires two images photographed at different time including an object to be identified, and a significant area detection section detects a significant area on the basis of a difference in the degrees of certainty of recognition by the object recognition device in the two images and a difference in featured values obtained by quantizing features in feature points included in the two images. The significant area includes a part of the object to be identified for improving the recognizing accuracy of the object recognition device. Also, the significant area detection section detects the significant area from any of the two images, and notifies a display section of the significant area.
摘要翻译：要解决的问题：提供一种识别支持装置，识别支持方法和程序，用于通过适当地拍摄受到对象识别的图像，在短时间内进行适当的对象识别。解决方案：在用于支持对象识别装置执行对象识别的识别支持装置中，图像获取部获取包括要识别的对象的不同时间拍摄的两个图像，并且有效区域检测部分检测对象识别装置的显着区域通过两个图像中的对象识别装置的识别确定度的差异的基础以及通过对包括在两个图像中的特征点中的特征进行量化而获得的特征值的差异。有意义的区域包括要识别的对象的一部分，以提高对象识别装置的识别精度。此外，有效区域检测部分从两个图像中的任何一个检测有效区域，并将显着区域通知显示部分。版权所有（C）2013，JPO＆INPIT

4. 发明专利

JP2012216207A Method and apparatus for acquiring descriptive information of plural images and image matching method 有权
标题翻译：用于获取平面图像和图像匹配方法的描述信息的方法和装置
公开(公告)号：JP2012216207A
公开(公告)日：2012-11-08
申请号：JP2012077535
申请日：2012-03-29
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ZHAO CHUN , LIU RUJIE , HAO YU , SUGIMURA MASAHIKO , UEHARA YUSUKE
IPC分类号： G06F17/30 , G06T1/00 , G06T7/00
CPC分类号： G06K9/4671 , G06K9/6857
摘要： PROBLEM TO BE SOLVED: To provide a method and apparatus for acquiring descriptive information of a plurality of images and an image matching method.SOLUTION: The method includes performing a feature point detection with respect to each image of the plurality of images so as to obtain a plurality of feature points of each image, and acquiring 0-level descriptive information of the plurality of images. The 0-level descriptive information of each image is generated in accordance with a plurality of first local feature descriptors for the image, obtained on the basis of the plurality of feature points of the image, and a plurality of first visual words, obtained on the basis of the plurality of first local feature descriptors for the plurality of images. For each image, a division of the image is performed n-1 times, so as to obtain a plurality of (n-1)-level sub-images; and (n-1)-level descriptive information is generated in accordance with a plurality of n-th local feature descriptors, obtained on the basis of the plurality of feature points and (n-1)-level sub-images where the respective feature points lie, and a plurality of n-th visual words, obtained on the basis of the plurality of n-th local feature descriptors, where n=2, 3, ..., K+1, and K is a positive integer.
摘要翻译：要解决的问题：提供一种用于获取多个图像的描述信息的方法和装置以及图像匹配方法。解决方案：该方法包括对多个图像中的每个图像执行特征点检测，以便获得每个图像的多个特征点，并且获取多个图像的0级描述信息。根据图像的多个特征点获得的多个用于图像的第一局部特征描述符，生成每个图像的0级描述信息，以及多个第一视觉词多个图像的多个第一局部特征描述符的基础。对于每个图像，执行图像的划分n-1次，以便获得多个（n-1）级的子图像; 和（n-1）级的描述信息根据多个第n个局部特征描述符生成，所述第n个局部特征描述符是基于多个特征点获得的，（n-1）个级别的子图像，其中各个特征以及基于多个第n个局部特征描述符获得的多个第n个视觉词，其中n = 2,3，...，K + 1和K是正整数。版权所有（C）2013，JPO＆INPIT

5. 发明专利

JP2012216200A Method and apparatus for camera motion analysis in video 有权
标题翻译：视频中摄像机运动分析的方法与装置
公开(公告)号：JP2012216200A
公开(公告)日：2012-11-08
申请号：JP2012065362
申请日：2012-03-22
申请人： Fujitsu Ltd , 富士通株式会社
发明人： YI BI , LIU RUJIE , HAO YU , BABA TAKAYUKI , UEHARA YUSUKE
IPC分类号： G06T7/20 , H04N5/225 , H04N5/232
CPC分类号： G06T7/20 , G06K9/00758
摘要： PROBLEM TO BE SOLVED: To provide methods etc. for camera motion analysis in a video.SOLUTION: A method includes: analyzing video segments with significant movement characteristics and video segments without any significant movement characteristic; for each video segment without any significant movement characteristic, if a first motion type corresponding to a preceding neighboring video segment is different from a second motion type corresponding to a succeeding neighboring video segment, lowering detection criteria of the first motion type and the second motion type; judging whether the video segment without any significant movement characteristic meets the lowered detection criteria; and merging the video segment without any significant movement characteristic with a neighboring video segment according to the result of judgment. With the embodiments of the invention, the motion type of a camera in the video can be detected more effectively and accurately, and the photographic intention of a user can be reflected more accurately.
摘要翻译：要解决的问题：为视频中的相机运动分析提供方法等。解决方案：一种方法包括：分析具有显着运动特征和视频段的视频段，而没有任何显着的移动特性; 对于每个视频段而没有任何显着的移动特征，如果对应于前一相邻视频段的第一运动类型与对应于后续相邻视频段的第二运动类型不同，则降低第一运动类型和第二运动类型的检测标准 ; 判断没有任何显着运动特性的视频段是否符合降低的检测标准; 并且根据判断结果与相邻视频段合并视频段而没有任何显着的移动特性。利用本发明的实施例，可以更有效和准确地检测视频中的相机的运动类型，并且可以更准确地反映用户的拍摄意图。版权所有（C）2013，JPO＆INPIT

6. 发明专利

JP2012195811A Digest image generating apparatus and program 有权
标题翻译：最佳图像生成设备和程序
公开(公告)号：JP2012195811A
公开(公告)日：2012-10-11
申请号：JP2011058967
申请日：2011-03-17
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ENDO SUSUMU , NAKAMURA SHUGO , ISHIHARA MASAKI , BABA TAKAYUKI , SUGIMURA MASAHIKO , UEHARA YUSUKE , MASUMOTO DAIKI , OSADA SHIGEMI
IPC分类号： H04N5/91 , G06F17/30 , G11B27/00 , G11B27/034
摘要： PROBLEM TO BE SOLVED: To provide a digest image generating apparatus capable of selecting an analytic processing parameter which improves an extraction result from among the candidates of analytic processing parameters to be executed in digest image generation.SOLUTION: A digest image generating apparatus 1 comprises: a correct answer section designation part 11 which designates a correct answer section indicating a section to be extracted as a digest image in an image 2; a parameter range setting part 12 which sets the range of change in the value of each analytic processing parameter on the basis of parameter information 4; a parameter change part 13 which changes the value of the analytic processing parameter within the set range; a digest image generating part 14 which analyzes the image 2 with the analytic processing parameter the value thereof and extracts a section determined to be the digest image; a coincidence calculation part 15 which calculates coincidence between the extracted section and a correct answer section 3; a parameter evaluation value calculation part 16 which calculates the evaluation value of the analytic processing parameter on the basis of the coincidence; and a parameter selection part 17 which selects the analytic processing parameter with a high evaluation value.
摘要翻译：要解决的问题：提供一种摘要图像生成装置，其能够从摘要图像生成中要执行的分析处理参数的候选中选择改善提取结果的分析处理参数。摘要图像产生装置1包括：正确答案部分指定部分11，其指定在图像2中指示要提取的部分作为摘要图像的正确答案部分; 参数范围设定部12，其基于参数信息4设定各分析处理参数的值的变化范围; 参数改变部13，其将分析处理参数的值改变到设定范围内; 摘要图像生成部分14，其利用分析处理参数将图像2分析其值，并提取确定为摘要图像的部分; 计算提取部分和正确答案部分3之间的一致性的符合计算部分15; 参数评价值计算部16，其基于一致性计算分析处理参数的评价值; 以及选择具有高评估值的分析处理参数的参数选择部17。版权所有（C）2013，JPO＆INPIT

7. 发明专利

JP2012160011A Thumbnail extraction program and thumbnail extraction method 有权
标题翻译：提取物提取方案和提取方法
公开(公告)号：JP2012160011A
公开(公告)日：2012-08-23
申请号：JP2011019158
申请日：2011-01-31
申请人： Fujitsu Ltd , 富士通株式会社
发明人： ENDO SUSUMU , ISHIHARA MASAKI , BABA TAKAYUKI , UEHARA YUSUKE , MASUMOTO DAIKI , NAKAMURA SHUGO , SUGIMURA MASAHIKO , OSADA SHIGEMI
IPC分类号： G06F17/30 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To provide a thumbnail extraction program and a thumbnail extraction method that are capable of extracting a thumbnail suitable for three-dimensional video.SOLUTION: A thumbnail extraction program causes a computer to execute processing for: extracting feature points corresponding between a frame image pair constituting one frame of 3D video from the frame image pair as a feature point pair; calculating a depth amount of the feature point pair based on a distance between points of the feature point pair, a distance between lenses, and a focal length, and clustering the feature point pair using the depth amount; evaluating stereoscopic visibility of one or more frame image pairs from clustering result information of the one or more frame image pairs on the basis of a predetermined evaluation condition of stereoscopic visibility of a frame image pair based on clustering result information; and extracting a pair of the frame image with the most excellent evaluation result as a pair of the frame image for a thumbnail based on the evaluation result of stereoscopic visibility.
摘要翻译：要解决的问题：提供能够提取适合于三维视频的缩略图的缩略图提取程序和缩略图提取方法。解决方案：缩略图提取程序使计算机执行以下处理：将构成来自帧图像对的一帧3D视频的帧图像对之间的对应的特征点提取为特征点对; 基于特征点对的点之间的距离，透镜之间的距离和焦距来计算特征点对的深度量，并且使用深度量对特征点对进行聚类; 基于基于聚类结果信息的帧图像对的立体可见度的预定评估条件，来评估一个或多个帧图像对的聚类结果信息的一个或多个帧图像对的立体可视性; 并且基于立体可视性的评估结果，以最优异的评估结果提取一对作为缩略图的帧图像的帧图像。版权所有（C）2012，JPO＆INPIT

8. 发明专利

JP2007287145A Shape comparing device and shape comparing method 有权
标题翻译：形状比较器件和形状比较方法
公开(公告)号：JP2007287145A
公开(公告)日：2007-11-01
申请号：JP2007103298
申请日：2007-04-10
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： G06T11/80
CPC分类号： G06K9/481
摘要： PROBLEM TO BE SOLVED: To provide a shape comparing device and a shape comparing method for computing the similarity of two objects based on the outline information of the objects. SOLUTION: The outlines of the objects drawn on an image is expressed converted into outline primitive sequence, and attribute values on outline primitives and outline primitive configuration are computed to compute similarity between the outlines while keeping the order of polygonal primitives. When input is not the outlines of the objects but the objects drawn on the image, the outlines of the objects drawn on the image in the objects drawn on the input image are extracted. COPYRIGHT: (C)2008,JPO&INPIT
摘要翻译：要解决的问题：提供一种形状比较装置和用于基于对象的轮廓信息来计算两个对象的相似度的形状比较方法。
解决方案：将图像上绘制的对象的轮廓表示为转换为轮廓原始序列，并计算轮廓图元和轮廓原始配置上的属性值，以计算轮廓之间的相似度，同时保持多边形基元的顺序。当输入不是对象的轮廓，而是在图像上绘制的对象时，提取在输入图像上绘制的对象中绘制在图像上的对象轮廓。版权所有（C）2008，JPO＆INPIT

9. 发明专利

JP2006318219A Similar slide retrieval program and retrieval method 审中-公开
标题翻译：类似的幻灯片检索程序和检索方法
公开(公告)号：JP2006318219A
公开(公告)日：2006-11-24
申请号：JP2005140135
申请日：2005-05-12
申请人： Fujitsu Ltd , 富士通株式会社
发明人： SHIITANI SHUICHI , ENDO SUSUMU , BABA TAKAYUKI , UEHARA YUSUKE , MASUMOTO DAIKI , OSADA SHIGEMI
IPC分类号： G06T7/00 , G06F17/30 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To perform similarity retrieval by only a layout, not depending on contents of a figure, and the kind or contents of a text.
SOLUTION: This similar slide retrieval program has: an area extraction part extracting a figure area, a text area, and a background area from a slide configured with the figure area, the text area, and the background area; an image generation part generating an image painting the extracted figure area, text area, and background area by different colors; and a characteristic calculation part calculating a layout characteristic comprising a ratio of the figure area to the generated image, a ratio of the text area to the generated image, and a ratio of the background area to the generated image; and a distance calculation part calculating a distance that is similarity of the layout characteristic.
COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：仅通过布局执行相似性检索，而不是依赖于图形的内容，以及文本的种类或内容。解决方案：这种相似的幻灯片检索程序具有：区域提取部分，从配置有图形区域，文本区域和背景区域的幻灯片提取图形区域，文本区域和背景区域; 图像生成部件，通过不同的颜色生成绘制提取的图形区域，文本区域和背景区域的图像; 以及特征计算部分，其计算布局特性，其包括所述图形区域与所生成的图像的比率，所述文本区域与所生成的图像的比率以及所述背景区域与所生成的图像的比率; 以及计算与布局特性相似的距离的距离计算部。版权所有（C）2007，JPO＆INPIT

10. 发明专利

JP2004341940A Similar image retrieval device, similar image retrieval method, and similar image retrieval program 有权
公开(公告)号：JP2004341940A
公开(公告)日：2004-12-02
申请号：JP2003139260
申请日：2003-05-16
申请人： Fujitsu Ltd , 富士通株式会社
发明人： BABA TAKAYUKI , MASUMOTO DAIKI , UEHARA YUSUKE , SHIITANI SHUICHI , ENDO SUSUMU
IPC分类号： G06T1/00 , G06F17/30 , G06T7/00 , H04N5/76 , H04N5/765 , H04N5/91
摘要： PROBLEM TO BE SOLVED: To enhance the efficiency of a similar image retrieval by speeding up the similar image retrieval of a plurality of inquiry images and generating an index of the plurality of inquiry images. SOLUTION: In this device, when a plurality of inquiry images are inputted to a large quantity of images that are retrieval objects, a similar image is outputted for each inquiry image as a retrieval result from the retrieval object images. This device comprises a means for extracting the characteristic quantities of the inquiry images, a means for generating an index for associating the inquiry images with each other, a means for extracting the characteristic quantities of the images that are retrieval objects, a means for generating an index for associating the retrieval object images with each other, a means for retrieving images similar to the inquiry images from the retrieval object images, and a means for outputting the similar image retrieval result. COPYRIGHT: (C)2005,JPO&NCIPI

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