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. 发明授权

US07551756B2 Process and device for detecting faces in a colour image 有权
标题翻译：用于检测彩色图像中的面部的过程和设备
公开(公告)号：US07551756B2
公开(公告)日：2009-06-23
申请号：US10887973
申请日：2004-07-08
申请人： Bertrand Chupeau , Vincent Tollu , Jürgen Stauder , Lionel Oisel
发明人： Bertrand Chupeau , Vincent Tollu , Jürgen Stauder , Lionel Oisel
IPC分类号： G06K9/00 , G06K9/62 , A61B1/04
CPC分类号： G06K9/00228
摘要： The invention relates to a device and a process for detecting faces in a colour image. The process is such that it comprises the steps of: detection of the flesh coloured pixels in the image, segmentation of the image into regions of homogeneous colour, selection, among the regions of homogeneous colour, of the regions comprising a number of flesh coloured pixels greater than a first predetermined threshold, the regions selected being said to be flesh coloured regions. merging of the neighbouring flesh coloured regions until the merge cost attains a second predetermined threshold, the merge cost linearly weighting a merge cost relating to the shape of the regions and a merge cost relating to the colour of the regions, exclusion of false positives.
摘要翻译：本发明涉及一种用于检测彩色图像中的面部的装置和方法。该过程包括以下步骤：检测图像中的肉色像素，将图像分割成均匀颜色的区域，在均匀颜色的区域中选择包括多个肉色像素的区域大于第一预定阈值，所选择的区域被称为肉色区域。将合并成本达到第二预定阈值，合并成本对与区域的形状有关的合并成本进行线性加权，以及与区域的颜色相关的合并成本，排除误报。

2. 发明授权

US07340096B2 Method for identification of tokens in video sequences 有权
标题翻译：用于识别视频序列中令牌的方法
公开(公告)号：US07340096B2
公开(公告)日：2008-03-04
申请号：US10800988
申请日：2004-03-15
申请人： Jürgen Stauder , Bertrand Chupeau , Lionel Oisel , Louis Chevallier
发明人： Jürgen Stauder , Bertrand Chupeau , Lionel Oisel , Louis Chevallier
IPC分类号： G06K9/46
CPC分类号： H04N5/222 , G06K9/3266
摘要： A method for identifying of tokens in a video sequence is described. First, the video sequence is scanned for boundaries between consecutive parts of the sequence where the appearance of the tokens is expected. After that step, candidate regions are pre-selected and classified in parts of the video sequence adjacent to detected boundaries, and tokens are located in the candidate regions. Information carried on the tokens is located, interpreted, and merged into consistent sets of information after passing a confidence analysis. In parallel a change in the visual appearance of a token, signaling a special event, is detected.
摘要翻译：描述了用于识别视频序列中的令牌的方法。首先，视频序列被扫描在序列的连续部分之间的边界，其中期望出现令牌的出现。在该步骤之后，候选区域被预选并分类为与检测到的边界相邻的视频序列的部分，并且令牌位于候选区域中。在通过信心分析之后，令牌上的信息被定位，解释和合并成一套一致的信息。并行地检测到令牌的视觉外观的改变，表示特殊事件。

3. 发明授权

US08510676B2 Method and device for creating semantic browsing options 有权
标题翻译：用于创建语义浏览选项的方法和设备
公开(公告)号：US08510676B2
公开(公告)日：2013-08-13
申请号：US10515534
申请日：2003-05-23
申请人： Jürgen Stauder , Loic Nunez , Bertrand Chupeau
发明人： Jürgen Stauder , Loic Nunez , Bertrand Chupeau
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30265
摘要： The invention concerns a device for creating semantic browsing options comprising a means to select an initial set of images from an input database comprising a plurality of images, each image being associated with a semantic information out of a semantic information space, a means to determine a semantic information sub-space represented by the semantic information associated with said initial set of images, The device comprises also: a means to select a reduced sub-space out of said sub-space, a means to create semantic links to images of the database associated with the semantic information of said reduced sub-space, a means to display at least one image of the database associated with the semantic information of said reduced sub-space.
摘要翻译：本发明涉及一种用于创建语义浏览选项的装置，包括从包括多个图像的输入数据库中选择一组初始图像的装置，每个图像与语义信息空间中的语义信息相关联，由与所述初始图像集相关联的语义信息表示的语义信息子空间。该装置还包括：从所述子空间中选择缩小的子空间的装置，用于创建到数据库的图像的语义链接的装置与所述缩减的子空间的语义信息相关联的装置，显示与所述缩小的子空间的语义信息相关联的数据库的至少一个图像的装置。

4. 发明授权

US08233743B2 Method and device for detecting the orientation of an image 有权
标题翻译：用于检测图像取向的方法和装置
公开(公告)号：US08233743B2
公开(公告)日：2012-07-31
申请号：US10584323
申请日：2005-01-04
申请人： Jürgen Stauder , Jean-Ronan Vigouroux , Bertrand Chupeau
发明人： Jürgen Stauder , Jean-Ronan Vigouroux , Bertrand Chupeau
IPC分类号： G06K9/32 , G09G5/00
CPC分类号： H04N1/3877 , G06K9/3208 , G06T7/74
摘要： The invention relates to a method and a device for detecting the orientation of an image in a set of images. All images in this set of images contain at least one similar object. The method proposes to choose one image in this set of images as being a reference image. The orientation of the other images is detected based on the orientation of this reference image.
摘要翻译：本发明涉及一种用于检测一组图像中的图像的取向的方法和装置。该组图像中的所有图像至少包含一个相似的对象。该方法建议在该组图像中选择一个图像作为参考图像。基于该参考图像的取向检测其他图像的取向。

5. 发明授权

US08164591B2 Device, server, system and method to generate mutual photometric effects 有权
标题翻译：设备，服务器，系统和方法来产生相互的光度效应
公开(公告)号：US08164591B2
公开(公告)日：2012-04-24
申请号：US10477586
申请日：2002-04-30
申请人： Jürgen Stauder , Bertrand Chupeau , Gérard Briand
发明人： Jürgen Stauder , Bertrand Chupeau , Gérard Briand
IPC分类号： G06T15/50
CPC分类号： G06T15/50
摘要： The invention concerns a device for generating mutual photometric effects and a server for delivering photometric parameters for generating mutual photometric effects and a system including such a device and such a server. The device comprises a receiver for receiving and demultiplexing the visual data sets and photometric parameters respectively associated with the data sets, a module for defining the mutual photometric effects to be generated for these photometric parameters, a compositor and a rendering module for positioning the visual data sets in the common support space and applying the effects defined for the photometric parameters from at least one of the visual data sets to at least one other of the visual data sets so that at least one visual data set influences one other visual data set in the common support space.
摘要翻译：本发明涉及用于产生相互测光效果的装置和用于传送用于产生相互测光效果的光度参数的服务器，以及包括这种装置和这种服务器的系统。该装置包括用于接收和解复用与数据集分别相关联的视觉数据集和光度参数的接收机，用于定义为这些测光参数产生的相互测光效果的模块，用于定位视觉数据的合成器和渲染模块设置在公共支撑空间中，并且将从至少一个视觉数据集合到光度参数定义的效果应用于视觉数据集中的至少一个视觉数据集，使得至少一个可视数据集影响视觉数据集中的另一个视觉数据集共同的支持空间。

6. 发明授权

US07847989B2 Method for conversion of a colour space using separate chromatic and luminance look-up tables 有权
标题翻译：使用单独的色度和亮度查找表转换色彩空间的方法
公开(公告)号：US07847989B2
公开(公告)日：2010-12-07
申请号：US11901615
申请日：2007-09-17
申请人： Laurent Blonde , Jürgen Stauder , Julien Thollot
发明人： Laurent Blonde , Jürgen Stauder , Julien Thollot
IPC分类号： G03F3/08
CPC分类号： H04N1/6019 , G06T11/001
摘要： According to the method, starting from the chromatic components xS, yS of the color vector to be converted, the components of an intermediate color vector RINT-CR, GINT-CR, ΣINT-CR are-interpolated, whose chromatic components, expressed in the source color space are: xINT-CR=xS, yINT-CR=yS; starting from the luminance component SS of the color vector to be converted and from the luminance component ΣINT-CR of the intermediate color vector, the luminance component ΣD of the converted color vector is interpolated; the chromatic components RD, GD of the converted color vector are calculated from its luminance component ΣD and from the components of the intermediate color vector RINT-CR, GINT-CR, ΣINT-CR. The conversion methods of the prior art are substantially improved.
摘要翻译：根据该方法，从要转换的颜色矢量的色分量xS，yS开始，中间色彩矢量RINT-CR，GINT-CR，＆Sgr; INT-CR的分量被插值，其色彩分量表示在源颜色空间中有：xINT-CR = xS，yINT-CR = yS; 从要转换的颜色矢量的亮度分量SS和从中间颜色矢量的亮度分量Sgr; INT-CR开始，内插经过转换的彩色矢量的亮度分量Sgr; D; 根据其亮度分量Sgr D和中间色彩矢量RINT-CR，GINT-CR，＆Sgr; INT-CR的分量计算转换后的彩色矢量的色彩分量RD，GD。现有技术的转换方法得到显着改善。

7. 发明申请

US20100128976A1 METHOD FOR DESCRIBING AN ACTUAL COLOR GAMUT OF A COLOR DEVICE OR OF A COLOR CONTENT 有权
标题翻译：用于描述彩色装置或彩色内容的实际彩色游戏的方法
公开(公告)号：US20100128976A1
公开(公告)日：2010-05-27
申请号：US12452744
申请日：2008-07-25
申请人： Jürgen Stauder , Laurent Blonde , Patrick Morvan
发明人： Jürgen Stauder , Laurent Blonde , Patrick Morvan
IPC分类号： G06K9/60
CPC分类号： H04N1/6058
摘要： To describe the actual color gamut, a hierarchical structure is proposed which comprises, from bottom to top: Gamut Components: each GC is a surface, generally described as a set of connected elementary triangles or polygons. Gamut Hulls: each GH is a closed surface formed by the concatenation of connex Gamut Components. Gamut Instances: each GI is an alternative Gamut Boundary Description of the same actual gamut and is built by the union of the volume(s) bordered by at least one Gamut Hull. Such a Gamut Boundary Information may be notably used for gamut mapping operations. Among advantages of the invention, are flexibility and adaptation to available memory and bandwidth capabilities.
摘要翻译：为了描述实际的色域，提出了从底部到顶部的分层结构：色域分量：每个GC是一个表面，通常被描述为一组连接的基本三角形或多边形。 Gamut Hulls：每个GH是通过连接器连接器组件形成的封闭表面。色域实例：每个GI是相同实际色域的替代色域边界描述，由至少一个Gamut Hull所界定的卷的联合构建。这样的色域边界信息可能特别用于色域映射操作。本发明的优点是灵活性和适应于可用存储器和带宽能力。

8. 发明授权

US08629881B2 Method of color mapping from non-convex source gamut into non-convex target gamut 有权
标题翻译：从非凸起源色域到非凸目标色域的颜色映射方法
公开(公告)号：US08629881B2
公开(公告)日：2014-01-14
申请号：US12452741
申请日：2008-07-25
申请人： Laurent Blonde , Jürgen Stauder , Wolfgang Endress
发明人： Laurent Blonde , Jürgen Stauder , Wolfgang Endress
IPC分类号： G09G5/02
CPC分类号： H04N1/6058
摘要： Method of mapping source colors from a source color device having an actual source gamut that is represented by a source convex (gamut boundary descriptor) and a source non-convex into target colors for a target color device having an actual target gamut that is represented by a target convex and a target non-convex, comprising, 1—if the source color to map is located outside the source non-convex, a pre-mapping step that maps the source color into the source non-convex, 2—if the mapped target color is located outside the target non-convex, a post-mapping step that maps the target color into the target non-convex. This method allows precise gamut mapping while allowing also for simple geometrical operations using convex gamuts.
摘要翻译：将具有由源凸（色域边界描述符）表示的实际源色域的源颜色和源非凸的源颜色的源颜色映射到具有实际目标色域的目标色彩设备的方法，所述目标色彩设备具有由目标凸和目标非凸，包括1 - 如果要映射的源颜色位于源非凸的外部，则将源颜色映射到源非凸的预映射步骤，2 - 如果映射的目标颜色位于目标非凸的外部，后映射步骤将目标颜色映射到目标非凸。该方法允许精确的色域映射，同时允许使用凸域的简单几何操作。

9. 发明申请

US20130033516A1 METHOD OF GENERATING A FINAL COLOUR VERSION OF A SOURCE IMAGE FROM A FIRST SET OF DIFFERENT INTERMEDIATE COLOUR VERSIONS 审中-公开
标题翻译：从第一组不同中间色彩版本中产生源图像的最终颜色版本的方法
公开(公告)号：US20130033516A1
公开(公告)日：2013-02-07
申请号：US13558310
申请日：2012-07-25
申请人： Jürgen Stauder , Hassane Guermoud , Laurent Blondé
发明人： Jürgen Stauder , Hassane Guermoud , Laurent Blondé
IPC分类号： G09G5/02
CPC分类号： H04N1/6013
摘要： This method comprises the following steps: displaying the different intermediate colour versions, from a visual comparison between displayed versions, selecting a second set, determining an intermediate colour transform able to transform an original version of said source image into each of said selected intermediate colour versions by a comparison between the original version of said source image with the selected intermediate colour version, building a final colour transform by combining each of the determined intermediate colour transforms, generating the final colour version by applying the built final colour transform to the original version of said source image.
摘要翻译：该方法包括以下步骤：从显示版本之间的视觉比较显示不同的中间色版本，选择第二组，确定能够将所述源图像的原始版本转换成所述所选择的中间色版本中的每一个的中间颜色变换通过将所述源图像的原始版本与所选择的中间颜色版本进行比较，通过组合每个所确定的中间颜色变换来构建最终颜色变换，通过将构建的最终颜色变换应用于原始版本的说源图像。

10. 发明申请

US20100053199A1 Image processing method and device implementing said method 有权
标题翻译：图像处理方法和装置实现所述方法
公开(公告)号：US20100053199A1
公开(公告)日：2010-03-04
申请号：US12448447
申请日：2007-12-17
申请人： Philippe Robert , Guylaine Le Jan , Jürgen Stauder
发明人： Philippe Robert , Guylaine Le Jan , Jürgen Stauder
IPC分类号： G09G5/02 , G09G5/00
CPC分类号： H04N9/68 , H04N9/646
摘要： The invention relates to a processing method of a sequence of images comprising image points each of which is associated with a colour component. The method comprises a processing step of at least one image of the sequence from reference images, the processing step being adapted to reduce the flicker effects. According to the invention, the reference images are selected according to the following stages: calculate, for at least one image part of each of the images of the sequence, the mean value of the colour component, the mean value being associated with the image, and a first selection step to select from the mean values a first series of reference images forming a subset of the sequence.
摘要翻译：本发明涉及包括与颜色分量相关联的图像点的图像序列的处理方法。该方法包括来自参考图像的序列的至少一个图像的处理步骤，该处理步骤适于减少闪烁效应。根据本发明，根据以下阶段选择参考图像：对于序列的每个图像的至少一个图像部分计算颜色分量的平均值，与图像相关联的平均值，以及第一选择步骤，从平均值中选择形成序列的子集的第一系列参考图像。

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