利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

529 条记录 (耗时 0.016 秒)

    DEVICE AND METHOD FOR CREATING A SALIENCY MAP OF AN IMAGE
    91.
    发明公开
    DEVICE AND METHOD FOR CREATING A SALIENCY MAP OF AN IMAGE 有权
    装置和方法，用于在图像中生成映射出尖锐特征

    公开(公告)号：EP1695288A1

    公开(公告)日：2006-08-30

    申请号：EP04804828.4

    申请日：2004-12-14

    申请人： Thomson Licensing

    发明人： LE MEUR, Olivier ,  THOREAU, Dominique ,  FRANCOIS, Edouard ,  LE CALLET, Patrick ,  BARBA, Dominique

    IPC分类号： G06T5/00 ,  G06T7/20

    CPC分类号： G06K9/4623 ,  G06K9/4652 ,  G06K9/4671 ,  G06T5/003 ,  G06T7/262 ,  G06T2207/10024

    摘要： The invention concerns a device and a method for creating a saliency map of an image. It comprises the steps of: Projection (E1) of said image according to the luminance (A) component and if said image is a color image, according to the luminance (A) component and according to the chrominance components (Cr1, Cr2); Perceptual sub-bands decomposition (E3, T2, T'2, T’’2) of said components (A, Cr1, Cr2) according to the visibility threshold of a human eye; Extraction (E7) of the salient elements of the sub-bands related to the luminance (A) component; Contour enhancement (E8, T7) of said salient elements in each sub-band related to the luminance (A) component; Calculation (T7) of a saliency map from the contour enhancement, for each sub-band related to the luminance (A) component. Creation (T8) of the saliency map as a function of the saliency maps obtained for each sub-band.

    METHOD FOR ROBUST SCALE-SPACE ANALYSIS OF 3D LOCAL STRUCTURES IN MEDICAL IMAGES
    92.
    发明公开
    METHOD FOR ROBUST SCALE-SPACE ANALYSIS OF 3D LOCAL STRUCTURES IN MEDICAL IMAGES 审中-公开
    VERFAHREN ZUR ROBUSTEN MASSSTABSRAUMANALSESE VON LOKALEN 3D-STRUKTUREN IN MEDIZINISCHEN BILDERN

    公开(公告)号：EP1646982A2

    公开(公告)日：2006-04-19

    申请号：EP04778656.1

    申请日：2004-07-19

    申请人： Siemens Medical Solutions USA, Inc.

    发明人： OKADA, Kazunori ,  COMANICIU, Dorin ,  BOGONI, Luca

    IPC分类号： G06T7/00

    CPC分类号： G06K9/4671 ,  G06T7/60 ,  G06T7/70 ,  G06T2200/04 ,  G06T2207/10072 ,  G06T2207/20016 ,  G06T2207/20101 ,  G06T2207/30096

    摘要： A method for determining the location, shape and orientation of a tumor in a medical image includes finding a plurality of spatial extrema µ of a D-dimensional spatial signal ƒ for a set of bandwidths H by performing (11) mean shift-based gradient-ascent iterations for a set of bandwidths H and then determining (12) a D-dimensional spread and orientation of the signal about each extrema µ by estimating a covariance Σ of the signal ƒ for each extrema µ . The optimal estimate of µ and Σ is determined by performing (13) a Jensen-Shannon divergence on the full set µ of and Σ .

    摘要翻译： 用于确定医学图像中的肿瘤的位置，形状和取向的方法包括：通过执行基于平均移位的梯度上升迭代来为一组带宽H找到D维空间信号f的多个空间极值mu 一组带宽H，然后通过估计每个极值mu的信号f的协方差Sigma来确定关于每个极值mu的信号的D维扩展和取向。 通过在全套mu和Sigma上执行Jensen-Shannon分歧来确定mu和Sigma的最优估计。

    VISUAL ATTENTION LOCATION SYSTEM
    95.
    发明公开
    VISUAL ATTENTION LOCATION SYSTEM 有权
    追踪系统视觉注意

    公开(公告)号：EP1281164A2

    公开(公告)日：2003-02-05

    申请号：EP01904110.2

    申请日：2001-02-08

    申请人： BRITISH TELECOMMUNICATIONS public limited company

    发明人： STENTIFORD, Frederick Warwick Michael

    IPC分类号： G06T7/00

    CPC分类号： G06K9/4671

    摘要： This invention identifies the most significant features in visual scenes, without prior training, by measuring the difficulty in finding similarities between neighbourhoods in the scene. Pixels in an area that is similar to much of the rest of the scene score low measures of visual attention. On the other hand a region that possesses many dissimilarities with other parts of the image will attract a high measure of visual attention. The invention makes use of a trial and error process to find dissimilarities between parts of the image and does not require prior knowledge of the nature of the anomalies that may be present. The method avoids the use of processing dependencies between pixels and is capable of a straightforward parallel implementation for each pixel. The invention is of wide application in searching for anomalous patterns in health screening, quality control processes and in analysis of visual ergonomics for assessing the visibility of signs and advertisements. The invention provides a measure of significant features to an image processor in order to provide variable rate image compression.

    System and method for counterfeit protection
    96.
    发明公开
    System and method for counterfeit protection 审中-公开
    系统和Verfahren zumFälschungsschutz

    公开(公告)号：EP1096433A2

    公开(公告)日：2001-05-02

    申请号：EP00118891.1

    申请日：2000-08-31

    申请人： Hewlett-Packard Company, A Delaware Corporation

    发明人： Keshet, Renato ,  Shaked, Doron

    IPC分类号： G07D7/20

    CPC分类号： G06K9/4671 ,  G06K9/4609 ,  G06K9/4652 ,  G07D7/20

    摘要： A system (10) and a method for preventing counterfeiting activities utilize an image detection scheme that uses only a few portions of restricted-document images, i.e., templates, to determine whether an input image is a duplicate of a restricted-document image. The image detection scheme can reliably operate at very low resolutions, which allows the use of small kernels for image correlation and reduces the number of pixels that have to be actually processed. The system is designed to be incorporated into a host device, such as a copy machine (12), a scanner (14), a personal computer (16) or a printer (18), to detect a potential counterfeiting activity, so that an appropriate action can be taken to prevent and/or to report the detected activity. The image detection scheme allows the system to operate at an increased detection speed, while minimizing the memory requirement. During an off-line training procedure, a training module (32) of the system derives a parameter file that contains detection descriptors for the restricted-document images, including threshold intervals that are defined using selected kernels and templates of the restricted-document images. The type of kernels and templates selected by the training module can vary, depending on the desired memory requirement and the desired on-line performance. During an on-line detection procedure, a detection module (24) of the system projects portions of the input image and compares the resulting projection value with the threshold intervals to derive template match candidates. The relative coordinates of the template match candidates in the input image are then compared with relative coordinates of the templates in the restricted-document images to determine if the input image matches a particular restricted-document image.

    摘要翻译： 系统（10）和防止假冒活动的方法利用仅使用少数限制文件图像（即，模板）的图像检测方案来确定输入图像是否是受限制文档图像的副本。 图像检测方案可以以非常低的分辨率可靠地运行，这允许使用小的内核进行图像相关，并减少必须实际处理的像素数量。 该系统被设计为并入到诸如复印机（12），扫描仪（14），个人计算机（16）或打印机（18）的主机设备中，以检测潜在的假冒活动，使得 可以采取适当的行动来防止和/或报告检测到的活动。 图像检测方案允许系统以提高的检测速度运行，同时最小化存储器需求。 在离线训练过程中，系统的训练模块（32）导出包含受限制文档图像的检测描述符的参数文件，包括使用所选择的内核和限制文档图像的模板定义的阈值间隔。 训练模块选择的内核和模板的类型可以根据所需的内存要求和所需的在线性能而有所不同。 在在线检测过程中，系统的检测模块（24）投影输入图像的部分，并将所得到的投影值与阈值间隔进行比较以得到模板匹配候选。 然后将输入图像中的模板匹配候选的相对坐标与限制文档图像中的模板的相对坐标进行比较，以确定输入图像是否与特定的限制文档图像匹配。

    A system and method for ranking and extracting salient contours for target recognition
    97.
    发明公开
    A system and method for ranking and extracting salient contours for target recognition 失效
    系统和方法，用于分类和用于靶识别的突出轮廓的提取。

    公开(公告)号：EP0506327A2

    公开(公告)日：1992-09-30

    申请号：EP92302501.9

    申请日：1992-03-24

    申请人： TEXAS INSTRUMENTS INCORPORATED

    发明人： Rao, Kashi

    IPC分类号： G06F15/66 ,  G06K9/46 ,  G06F15/68

    CPC分类号： G06K9/3241 ,  G06K9/4604 ,  G06K9/4609 ,  G06K9/4671 ,  G06T7/12 ,  G06T7/181 ,  G06T2207/10016 ,  G06T2207/10032 ,  G06T2207/10048 ,  G06T2207/20016 ,  G06T2207/30212

    摘要： A system and method for obtaining salient contours from two-dimensional images acquired by a sensor (15) is disclosed which process the two-dimensional images with an edge detector (20) to produce edgels from each of the images, link the edgels into lists (25) known as contours, compute a saliency value (30) for each of the contours, rank the contours (60) in decreasing order of saliency, and select certain ones of the ranked contours based on the requirements of a particular vision application (65).
    Other devices, systems and methods are also disclosed.

    摘要翻译： 一种用于从由传感器获取的二维图像获取凸轮廓的系统和方法（15）是圆盘游离缺失哪些在边缘检测器（20），以从每个图像产生edgels处理与所述二维图像，所述edgels链接到列表 （25）称为轮廓，计算每个轮廓的显着性值（30），排列的轮廓（60）显着减少的顺序，选择基于特定视觉应用​​的要求，排轮廓中的某些（ 65）。 因此其他设备，系统和方法游离缺失盘。

    FEATURE VECTOR GENERATION AND ENCRYPTION
    98.
    发明公开
    FEATURE VECTOR GENERATION AND ENCRYPTION 审中-公开

    公开(公告)号：EP3410352A1

    公开(公告)日：2018-12-05

    申请号：EP18167897.0

    申请日：2018-04-18

    申请人： FUJITSU LIMITED

    发明人： MANDAL, Avradip ,  ROY, Arnab ,  MONTGOMERY, Hart ,  DATTA, Nilanjan

    IPC分类号： G06K9/46 ,  G06K9/62 ,  G06F21/60

    CPC分类号： G06K9/481 ,  G06F21/602 ,  G06K9/4642 ,  G06K9/4671 ,  G06K9/6202 ,  G06K9/6215 ,  G06K9/6232

    摘要： A method may include extracting feature-data from an image which includes location data that indicates multiple locations within the image and multiple feature vectors that each correspond to one of the multiple locations. Each feature vector may represent a feature of an object in the image. The method may include determining a feature-data plot based on relative positions of the multiple locations and selecting a grid for the feature-data plot. The method may include generating a first representative feature vector for a first cell of the grid based on a first feature vector set and generating a second representative feature vector for a second cell of the grid based on a second feature vector set. The method may include generating a single feature vector that represents the object in the image based on the first representative feature vector and the second representative feature vector and encrypting the single feature vector.