会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明专利
    • Image processor
    • 图像处理器
    • JP2006309641A
    • 2006-11-09
    • JP2005133979
    • 2005-05-02
    • Mitsubishi Electric Corp三菱電機株式会社
    • TAKAHASHI NAMIOKUDA HARUHISAHASHIMOTO MANABU
    • G06T7/00G06T1/00
    • PROBLEM TO BE SOLVED: To provide an image processor for correctly recognizing an image having a complicated background even when a target stands still, and the target size is small on the image by discriminating the target from anything other than the target.
      SOLUTION: This image processor is provided with an image storing means for storing image data, a target candidate storing means for storing the data of the position or scale of a target candidate in an image, a target region featured value calculating means for calculating featured values including at least one of luminance information, color information, texture information or gradient information of a target candidate region, a peripheral region model generating means for generating the peripheral model of the periphery of the target candidate for the featured values including at least one of the luminance information, color information, texture information or gradient information of the peripheral region of the target candidate, and a deciding means for deciding the authenticity of the target candidate by calculating the level of separation of the featured values of the target region calculated by the target region featured value calculating means from the peripheral model calculated by the peripheral region model generating means.
      COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:为了提供一种图像处理器,即使在目标静止时也正确地识别具有复杂背景的图像,并且通过将目标与目标之外的任何目标区分开来,图像上的目标尺寸小。 解决方案:该图像处理器设置有用于存储图像数据的图像存储装置,用于存储图像中的目标候选者的位置或比例的数据的目标候选存储装置,目标区域特征值计算装置, 计算包括目标候选区域的亮度信息,颜色信息,纹理信息或梯度信息中的至少一个的特征值,周边区域模型生成装置,用于生成包括至少包括的特征值的目标候选者的外围的外围模型 目标候选者的周边区域的亮度信息,颜色信息,纹理信息或梯度信息之一,以及通过计算计算出的目标区域的特征值的分离水平来判定目标候选者的真实性的判定装置 由外围模型计算的目标区域特征值计算装置 由周边区域模型生成装置执行。 版权所有(C)2007,JPO&INPIT
    • 3. 发明专利
    • Image retrieval device
    • 图像检索装置
    • JP2005242889A
    • 2005-09-08
    • JP2004054578
    • 2004-02-27
    • Mitsubishi Electric Corp三菱電機株式会社
    • TAKAHASHI NAMIOKUDA HARUHISAHASHIMOTO MANABU
    • G06F17/30G06T7/00
    • PROBLEM TO BE SOLVED: To provide an image retrieval device capable of performing a precise retrieval while suppressing an increase in processing time even in case that retrieval object images are increased.
      SOLUTION: A reference image characteristic quantity extraction means 2 extracts the characteristic quantity of a reference image. This reference image characteristic quantity is converted to a retrieval area characteristic quantity by a characteristic quantity conversion means 4. A retrieval area extraction means 6 extracts an area corresponding to the retrieval area characteristic quantity converted by the means 4 from retrieval object images stored in a retrieval object image group storage means 5 as a retrieval processing area. An image collation means 7 collates the retrieval processing area extracted from the retrieval object images by the means 6 with the reference image to determine the similarity of both the images.
      COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供一种即使在检索对象图像增加的情况下也能够抑制处理时间的增加而能够执行精确检索的图像检索装置。 参考图像特征量提取装置2提取参考图像的特征量。 该参考图像特征量通过特征量转换装置4转换为检索区域特征量。检索区域提取装置6从存储在检索中的检索对象图像中提取与由装置4转换的检索区域特征量相对应的区域 对象图像组存储装置5作为检索处理区域。 图像对照装置7将通过装置6从检索对象图像提取的检索处理区域与参考图像进行核对,以确定两个图像的相似度。 版权所有(C)2005,JPO&NCIPI
    • 4. 发明专利
    • Device for identifying object of detection
    • 用于识别检测对象的设备
    • JP2005202860A
    • 2005-07-28
    • JP2004010732
    • 2004-01-19
    • Mitsubishi Electric Corp三菱電機株式会社
    • KAGE YASUSHIHASHIMOTO MANABU
    • A61B5/117G06T1/00G06T7/00G06T7/60
    • PROBLEM TO BE SOLVED: To provide a device for identifying the object of detection that is capable of quickly beginning the process of identifying the object of detection and of determining in a short time whether there is the object of detection. SOLUTION: A filtering part 6 that applies a Walsh-Hadamard transform filter to an image in an area 22 of the object of analysis every time an area segmenting part 5 cuts out the area 22, and a memory 3 that stores the results of application of the two-dimensional Walsh-Hadamard transform filter to a form face image 16 showing the object of detection are provided. The result of application by the filtering part 6 is collated with the result of application stored in the memory 3 to determine whether the image of the area 22 shows a face. COPYRIGHT: (C)2005,JPO&NCIPI
    • 要解决的问题:提供一种用于识别能够快速开始识别检测对象的处理并且在短时间内确定是否存在检测对象的检测对象的设备。 解决方案:每当区域分割部分5切出区域22时,对分析对象的区域22中的图像应用沃尔什 - 哈达玛变换滤波器的滤波部分6以及存储结果的存储器3 提供了将二维沃尔什 - 哈达玛变换滤波器应用于表示检测对象的表单图像16。 将过滤部分6的应用结果与存储在存储器3中的应用结果进行整理,以确定区域22的图像是否显示面部。 版权所有(C)2005,JPO&NCIPI
    • 5. 发明专利
    • Three-dimensional shape measuring instrument
    • 三维形状测量仪器
    • JP2003329424A
    • 2003-11-19
    • JP2002138313
    • 2002-05-14
    • Mitsubishi Electric Corp三菱電機株式会社
    • OKUDA HARUHISAHASHIMOTO MANABUWASHIMI KAZUHIKO
    • G01B11/00G01B11/24
    • PROBLEM TO BE SOLVED: To easily perform the focusing and slit space adjustment by the optical path difference, and to easily adjust the focus and the position when performing the three-dimensional shape measurement by utilizing a rear-view mirror.
      SOLUTION: The three-dimensional shape measuring instrument comprises an image accumulation device 16 to accumulate image signals 202 obtained by picking up images, an operation unit 17 to perform conversion from an image pickup coordinate system of a measurement point on an object 1 for measurement which is measured by an image pickup device 11 to an absolute coordinate system on the object 1 for measurement, a mirror 13 which is installed so as to be present in a visual field area of the image pickup device 11, and has a mirror surface characteristic or the reflection characteristic equivalent thereto in a wavelength area which is observed by the image pickup device 11, and further comprises an operation switching means 18 which uses a coordinates conversion calculation formula depending on the installation position of the mirror 13 for a part of the object 1 to be measured via the mirror 13, and uses a coordinates conversion calculation formula of direct measurement for a direct measurement part of the object 1 to be directly measured.
      COPYRIGHT: (C)2004,JPO
    • 要解决的问题:为了容易地通过光程差进行聚焦和狭缝空间调节,并且通过利用后视镜来执行三维形状测量时容易地调节聚焦和位置。 解决方案:三维形状测量仪器包括:图像累积装置16,用于累积通过拍摄图像获得的图像信号;操作单元17,用于从物体1上的测量点的摄像坐标系进行转换; 用于由图像拾取装置11测量到用于测量的对象1上的绝对坐标系的测量;反射镜13,安装成存在于图像拾取装置11的视野区域中,并具有镜子 表面特性或与图像拾取装置11所观察到的波长区域相当的反射特性,还包括操作切换装置18,该操作切换装置18根据反射镜13的一部分的安装位置使用坐标转换计算公式 经由反射镜13测量的物体1,并使用直接测量直接测量的坐标转换计算公式 物体1的测量部分要直接测量。 版权所有(C)2004,JPO
    • 6. 发明专利
    • Image and television broadcast receiver with sound communication function
    • 具有声音通信功能的图像和电视广播接收器
    • JP2007300452A
    • 2007-11-15
    • JP2006127298
    • 2006-05-01
    • Mitsubishi Electric Corp三菱電機株式会社
    • YAGI KOSUKEFUKUDA TOMOKAZUKUSHIDA TAKAYUKINAGASE AKIHIROODA KYOICHIROKAWADA KAORUHASHIMOTO MANABUYOSHIHARA TORUOHASHI TOMONORI
    • H04N7/15H04M1/00H04N5/45H04N7/173
    • PROBLEM TO BE SOLVED: To allow a display dimension by each screen on a synthetic screen to be switchable in cooperation with a program content and the importance degree of each attendant in the conversation of a video conference. SOLUTION: A television broadcast receiver with a sound communication function includes: a video decoding part 22 for decoding a television broadcast; an image and sound adjusting part 13 for converting an input signal into a form suitable for communication processing; a communication decoding part 34 for decoding the input signal from a communication line; a communication control part 32 for controlling an input/output signal relative to the communication line; an image composing part 14 for outputting the composite image signal of image signals from the video decoding part 22 and the communication decoding part 34; a display part 15 for displaying the composite image signal; and a conversation state determining part 41 for determining a conversation state between a user and a communication opposite party, based on respective sound signals from the image and sound adjusting part 13 and the communication decoding part 34, and outputting a synthetic control signal. The image composing part 14 composes the composite image signal, based on the composite control signal to be inputted from the conversation state determining part 41, and displays it in the display part 15. COPYRIGHT: (C)2008,JPO&INPIT
    • 要解决的问题:允许合成屏幕上的每个屏幕的显示尺寸可以与节目内容合作切换,并且允许每个伴随者在视频会议的对话中的重要程度。 解决方案:具有声音通信功能的电视广播接收机包括:用于解码电视广播的视频解码部分22; 用于将输入信号转换成适于通信处理的形式的图像和声音调整部分13; 通信解码部分34,用于对来自通信线路的输入信号进行解码; 用于控制相对于通信线路的输入/输出信号的通信控制部分32; 用于从视频解码部分22和通信解码部分34输出图像信号的合成图像信号的图像合成部分14; 用于显示合成图像信号的显示部分15; 以及用于基于来自图像和声音调整部分13和通信解码部分34的各个声音信号来确定用户和通信对方之间的对话状态的会话状态确定部分41,并输出合成控制信号。 图像合成部14基于从通话状态判定部41输入的复合控制信号,构成合成图像信号,并将其显示在显示部15中。(C)2008,JPO&INPIT
    • 7. 发明专利
    • Image-detecting device
    • 图像检测装置
    • JP2007025935A
    • 2007-02-01
    • JP2005205226
    • 2005-07-14
    • Mitsubishi Electric Corp三菱電機株式会社
    • HIRASAWA HIROSUKEKAGE YASUSHIHASHIMOTO MANABUSHINBOU KENICHIMATSUOKA NOBUYUKITANAKA KENJI
    • G06T1/00G06T5/00G06T7/00H04N1/407
    • PROBLEM TO BE SOLVED: To provide an image-detecting device which very precisely detects a part in which a face is painted from an image. SOLUTION: The image-detecting device 10 is provided with; an original image acquisition part 12 which acquires an original image from which a face part is detected; an original image tone curve correction part 22 which makes a correction to the original image by using a first tone curve line to generate a corrected original image; a face image generation part 24 which detects a face part in the corrected original image and generates a face image; a face image tone curve correction part 26 which makes a correction to the face image by using one of a plurality of second tone curve lines and generates a plurality of corrected face images to which different corrections are made; a face image evaluation part 28 which evaluates the certainty of a face image for each of the plurality of corrected face images; and a tone curve line computation part 30 which computes the first tone curve line based on the second tone curve line which the face image tone curve correction part applies to a corrected face image to which the face image evaluation part gives the highest evaluation. COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供一种图像检测装置,其非常精确地检测从图像中涂上脸部的部分。

      解决方案:图像检测装置10设置有: 原始图像获取部12,其获取检测到脸部的原始图像; 原始图像色调曲线校正部分22,通过使用第一色调曲线对原始图像进行校正以产生校正的原始图像; 面部图像生成部24,其检测修正后的原图像中的脸部,生成面部图像; 面部图像色调曲线校正部26,其通过使用多个第二色调曲线中的一个对面部图像进行校正,并生成对其进行不同的校正的多个校正脸部图像; 面部图像评价部28,评价多个校正面部图像中的每一个的面部图像的确定性; 以及基于面部图像色调曲线校正部分应用于面部图像评价部分给出最高评价的校正脸部图像的第二色调曲线计算第一色调曲线的色调曲线计算部分30。 版权所有(C)2007,JPO&INPIT

    • 8. 发明专利
    • Three-dimensional object collation device
    • 三维物体收集装置
    • JP2005293350A
    • 2005-10-20
    • JP2004108990
    • 2004-04-01
    • Mitsubishi Electric Corp三菱電機株式会社
    • OKUDA HARUHISAHASHIMOTO MANABU
    • G01B11/24G06T1/00
    • PROBLEM TO BE SOLVED: To provide a three-dimensional object collation device capable of collating a three-dimentional object speedly and highly precisely while reducing the influence of a measurement error by a sensor in order to realize a collation performance high in practicality.
      SOLUTION: The three-dimensional object collation device is provided with: an error characteristic evaluation means 14 for estimating the measurement error for each measuring point of three-dimensional data; a featured part extraction means 16 for segmenting one or more data areas from the three-dimensional data and selecting a data area with data distribution larger than a threshold as an initial candidate; a processing time/accuracy evaluation time 18 for calculating estimation processing time and estimation collation accuracy for the data areas or combination of the data areas; and a collation data selection means 10 for selecting the data areas or combination of the data areas for achieving target processing time and target collation accuracy from the initial candidate. A three-dimensional data collation means performs the collation with standard three-dimensional data for the data area or a combination of the data areas selected by the collation data area selection means 10.
      COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:为了提供能够快速,高精度地对齐三维物体的三维物体对准装置,同时减少传感器的测量误差的影响,以便实现高实用性的核对性能 。 解决方案:三维物体核对装置设置有:用于估计三维数据的每个测量点的测量误差的误差特性评估装置14; 特征部分提取装置16,用于从三维数据分割一个或多个数据区域,并选择具有大于阈值的数据分布的数据区域作为初始候选; 用于计算数据区域或数据区域的组合的估计处理时间和估计对照精度的处理时间/精度评估时间18; 以及对照数据选择装置10,用于从初始候选者中选择用于实现目标处理时间的数据区域或数据区域的组合以及目标对照精度。 三维数据对照装置对数据区域的标准三维数据或由对照数据区域选择装置10选择的数据区域的组合执行核对。(C)2006年,JPO和NCIPI
    • 10. 发明专利
    • Monitoring system having masking function, camera, mask releasing device used with camera
    • 具有遮罩功能的监控系统,摄像机使用的面罩释放装置
    • JP2005286468A
    • 2005-10-13
    • JP2004094384
    • 2004-03-29
    • Mitsubishi Electric Corp三菱電機株式会社
    • TANIGUCHI HIROYASUSEKI MAKITOHASHIMOTO MANABU
    • G06T1/00G08B25/00H04N5/225H04N5/232H04N5/262H04N7/18
    • G08B13/19686
    • PROBLEM TO BE SOLVED: To provide a monitoring system for making a mask to be released according to the authority of an observer different even if there are a plurality of observers having a mask release right.
      SOLUTION: The monitoring system 2 comprises an imaging section 4; a masking section 6 that creates a mask image in which an object is masked when at least one object to be masked is included in an original image captured by the imaging section, and generates mask information for indicating position/size on the original image at a mask region regarding each object and the type of the object; an unmask processor 48 for releasing the mask of a mask image, based on the mask information; a storage 52 that stores a table for indicating the correspondence between the observer who monitors the mask image and the type of the object that can be observed by the observer; and a control unit 50 that refers to the table when a command is received from an observer via an input 54, and controls the unmask processor so that only a mask regarding the type of object corresponding to the observer is released.
      COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:提供一种监视系统,用于根据观察者的权限使掩模释放,即使存在具有掩模释放权的多个观察者也是如此。

      解决方案:监视系统2包括成像部分4; 当由至少一个要被遮蔽的对象被遮蔽的对象被掩蔽的掩模图像被包含在由成像部分拍摄的原始图像中时,屏蔽部分6产生用于指示原始图像上的位置/尺寸的掩模信息 关于每个对象的掩模区域和对象的类型; 基于掩码信息,释放掩模图像的掩模的解掩码处理器48; 存储用于指示监视掩模图像的观察者与观察者可以观察到的对象的类型之间的对应关系的表的存储器52; 以及控制单元50,其通过输入54从观察者接收到命令时参考该表,并且控制该非屏蔽处理器,使得仅释放与该观察者对应的对象的类型的掩码。 版权所有(C)2006,JPO&NCIPI