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. 发明申请

US20120075329A1 SYSTEM AND METHOD FOR IMAGE COLOR TRANSFER BASED ON TARGET CONCEPTS 有权
标题翻译：基于目标概念的图像色彩传输系统与方法
公开(公告)号：US20120075329A1
公开(公告)日：2012-03-29
申请号：US12890049
申请日：2010-09-24
申请人： Sandra Skaff , Naila Murray , Luca Marchesotti , Florent Perronnin
发明人： Sandra Skaff , Naila Murray , Luca Marchesotti , Florent Perronnin
IPC分类号： G09G5/02
CPC分类号： G09G5/06 , G06N7/005 , G09G2320/0606 , G09G2320/0666
摘要： A system and method for color transfer are provided. The method includes retrieving a concept color palette from computer memory corresponding to a concept selected by a user. The concept color palette includes a first set of colors, which may be statistically representative of colors of a set of predefined color palettes which have been associated with the concept. The method further includes computing an image color palette for an input image. The image color palette includes a second set of colors that are representative of pixels of the input image. Colors of the image color palette are mapped to colors of the concept color palette to identify, for colors of the image color palette, a corresponding color in the concept color palette. A transformation is computed based on the mapping. For pixels of the input image, modified color values are computed, based on the computed transformation, to generate a modified image.
摘要翻译：提供了一种用于颜色转移的系统和方法。该方法包括从与用户选择的概念对应的计算机存储器检索概念调色板。概念调色板包括第一组颜色，其可以统计代表已经与该概念相关联的一组预定义调色板的颜色。该方法还包括计算用于输入图像的图像调色板。图像调色板包括代表输入图像的像素的第二组颜色。图像调色板的颜色被映射到概念调色板的颜色，以针对图像调色板的颜色识别概念调色板中的对应颜色。基于映射计算变换。对于输入图像的像素，基于所计算的变换来计算修改的颜色值以生成修改的图像。

2. 发明授权

US08553045B2 System and method for image color transfer based on target concepts 有权
标题翻译：基于目标概念的图像颜色传输系统和方法
公开(公告)号：US08553045B2
公开(公告)日：2013-10-08
申请号：US12890049
申请日：2010-09-24
申请人： Sandra Skaff , Naila Murray , Luca Marchesotti , Florent Perronnin
发明人： Sandra Skaff , Naila Murray , Luca Marchesotti , Florent Perronnin
IPC分类号： G09G5/02
CPC分类号： G09G5/06 , G06N7/005 , G09G2320/0606 , G09G2320/0666
摘要： A method for color transfer includes retrieving a concept color palette from computer memory corresponding to a concept selected by a user. The concept color palette includes a first set of colors, which may be statistically representative of colors of a set of predefined color palettes which have been associated with the concept. The method further includes computing an image color palette for an input image. The image color palette includes a second set of colors that are representative of pixels of the input image. Colors of the image color palette are mapped to colors of the concept color palette to identify, for colors of the image color palette, a corresponding color in the concept color palette. A transformation is computed based on the mapping. For pixels of the input image, modified color values are computed, based on the computed transformation, to generate a modified image.
摘要翻译：用于颜色传送的方法包括从与用户选择的概念对应的计算机存储器检索概念调色板。概念调色板包括第一组颜色，其可以统计代表已经与该概念相关联的一组预定义调色板的颜色。该方法还包括计算用于输入图像的图像调色板。图像调色板包括代表输入图像的像素的第二组颜色。图像调色板的颜色被映射到概念调色板的颜色，以针对图像调色板的颜色识别概念调色板中的对应颜色。基于映射计算变换。对于输入图像的像素，基于所计算的变换来计算修改的颜色值以生成修改的图像。

3. 发明授权

US08379974B2 Convex clustering for chromatic content modeling 有权
标题翻译：用于彩色内容建模的凸聚类
公开(公告)号：US08379974B2
公开(公告)日：2013-02-19
申请号：US12975753
申请日：2010-12-22
申请人： Naila Murray , Florent Perronnin , Luca Marchesotti , Sandra Skaff
发明人： Naila Murray , Florent Perronnin , Luca Marchesotti , Sandra Skaff
IPC分类号： G06K9/00
CPC分类号： G06K9/4652 , G06K9/6222 , G06N7/005 , G06T7/11 , G06T7/143 , G06T7/90 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081
摘要： A system and method are provided for modeling a chromatic object, such as an image. For a set of colors of a chromatic object that are expressed as color values in a perceptual color space, the method includes optimizing a convex objective function which is a log likelihood function of a combination of weighted kernels centered on each color in the set over each of the other colors in the set. A number Nc of weighted kernels in the optimized function which each have a weight which is at least greater than 0 is identified. The chromatic object is modeled with a mixture model in which the complexity of the model is based on the identified number Nc.
摘要翻译：提供了一种用于对诸如图像的彩色物体进行建模的系统和方法。对于在感知色彩空间中表示为彩色值的彩色物体的一组颜色，该方法包括优化凸目标函数，该目标函数是集中在每组中的每种颜色的加权核的组合的对数似然函数的集合中的其他颜色。确定每个具有至少大于0的权重的优化函数中的N c个加权内核。彩色物体用混合模型建模，其中模型的复杂性基于识别的数量Nc。

4. 发明申请

US20120163715A1 CONVEX CLUSTERING FOR CHROMATIC CONTENT MODELING 有权
标题翻译： CONVEX聚类用于色彩内容建模
公开(公告)号：US20120163715A1
公开(公告)日：2012-06-28
申请号：US12975753
申请日：2010-12-22
申请人： NAILA MURRAY , Florent Perronnin , Luca Marchesotti , Sandra Skaff
发明人： NAILA MURRAY , Florent Perronnin , Luca Marchesotti , Sandra Skaff
IPC分类号： G06K9/00
CPC分类号： G06K9/4652 , G06K9/6222 , G06N7/005 , G06T7/11 , G06T7/143 , G06T7/90 , G06T2207/10024 , G06T2207/20076 , G06T2207/20081
摘要： A system and method are provided for modeling a chromatic object, such as an image. For a set of colors of a chromatic object that are expressed as color values in a perceptual color space, the method includes optimizing a convex objective function which is a log likelihood function of a combination of weighted kernels centered on each color in the set over each of the other colors in the set. A number Nc of weighted kernels in the optimized function which each have a weight which is at least greater than 0 is identified. The chromatic object is modeled with a mixture model in which the complexity of the model is based on the identified number Nc.
摘要翻译：提供了一种用于对诸如图像的彩色物体进行建模的系统和方法。对于在感知色彩空间中表示为彩色值的彩色物体的一组颜色，该方法包括优化凸目标函数，该目标函数是集中在每组中的每种颜色的加权核的组合的对数似然函数的集合中的其他颜色。确定每个具有至少大于0的权重的优化函数中的N c个加权内核。彩色物体用混合模型建模，其中模型的复杂性基于识别的数量Nc。

5. 发明申请

US20120269425A1 PREDICTING THE AESTHETIC VALUE OF AN IMAGE 有权
标题翻译：预测图像的美学价值
公开(公告)号：US20120269425A1
公开(公告)日：2012-10-25
申请号：US13089504
申请日：2011-04-19
申请人： Luca Marchesotti , Florent Perronnin , Gabriela Csurka
发明人： Luca Marchesotti , Florent Perronnin , Gabriela Csurka
IPC分类号： G06K9/62 , G06K9/00 , G06K9/48 , G06K9/46
CPC分类号： G06N99/005 , G06K9/036 , G06K9/6277 , G06T7/0002 , G06T2207/30168
摘要： A system and method for determining the aesthetic quality of an image are disclosed. The method includes extracting a set of local features from the image, such as gradient and/or color features and generating an image representation which describes the distribution of the local features. A classifier system is used for determining an aesthetic quality of the image based on the computed image representation.
摘要翻译：公开了一种用于确定图像的美学质量的系统和方法。该方法包括从图像提取一组局部特征，例如梯度和/或颜色特征，并且生成描述局部特征分布的图像表示。分类器系统用于基于所计算的图像表示来确定图像的美学质量。

6. 发明授权

US08594385B2 Predicting the aesthetic value of an image 有权
标题翻译：预测图像的美学价值
公开(公告)号：US08594385B2
公开(公告)日：2013-11-26
申请号：US13089504
申请日：2011-04-19
申请人： Luca Marchesotti , Florent Perronnin , Gabriela Csurka
发明人： Luca Marchesotti , Florent Perronnin , Gabriela Csurka
IPC分类号： G06K9/00
CPC分类号： G06N99/005 , G06K9/036 , G06K9/6277 , G06T7/0002 , G06T2207/30168
摘要： A system and method for determining the aesthetic quality of an image are disclosed. The method includes extracting a set of local features from the image, such as gradient and/or color features and generating an image representation which describes the distribution of the local features. A classifier system is used for determining an aesthetic quality of the image based on the computed image representation.
摘要翻译：公开了一种用于确定图像的美学质量的系统和方法。该方法包括从图像提取一组局部特征，例如梯度和/或颜色特征，并且生成描述局部特征分布的图像表示。分类器系统用于基于所计算的图像表示来确定图像的美学质量。

7. 发明申请

US20110276872A1 DYNAMIC FONT REPLACEMENT 审中-公开
标题翻译：动态替换
公开(公告)号：US20110276872A1
公开(公告)日：2011-11-10
申请号：US12774819
申请日：2010-05-06
申请人： Saurabh Kataria , Luca Marchesotti , Florent Perronnin
发明人： Saurabh Kataria , Luca Marchesotti , Florent Perronnin
IPC分类号： G06F17/21 , G06F17/00 , G06F3/048
CPC分类号： G06F17/214
摘要： Automated font mapping is performed for one or more document fonts of a document to map the one or more document fonts to at least one replacement font. The font mapping is limited by at least one document-specific font mapping limitation. The document is rendered using the at least one replacement font. The automated font mapping may include performing a constrained optimization of an objective function measuring similarity of the one or more document fonts and the corresponding mapped at least one replacement font, the constrained optimization being constrained by at least one constraint embodying at least one document-specific font mapping limitation. The automated font mapping may include selecting a subset of the set of fonts available for the rendering based on the at least one document-specific font mapping limitation, and performing the optimization respective to the selected subset of the set of fonts available for the rendering.
摘要翻译：对文档的一个或多个文档字体执行自动字体映射，以将一个或多个文档字体映射到至少一个替换字体。字体映射受到至少一个文档特定字体映射限制的限制。使用至少一个替换字体呈现文档。自动字体映射可以包括执行测量一个或多个文档字体和对应的映射的至少一个替换字体的相似性的目标函数的约束优化，所述约束优化受到体现至少一个文档特定的至少一个约束的约束字体映射限制。自动字体映射可以包括基于至少一个文档特定字体映射限制来选择可用于呈现的一组字体的子集，以及对可用于呈现的一组字体的所选择的子集进行优化。

8. 发明授权

US08824742B2 Occupancy detection for managed lane enforcement based on localization and classification of windshield images 有权
标题翻译：基于挡风玻璃图像的本地化和分类的管理车道执行的占用检测
公开(公告)号：US08824742B2
公开(公告)日：2014-09-02
申请号：US13527228
申请日：2012-06-19
申请人： Sandra Skaff , Beilei Xu , Peter Paul , Craig Saunders , Florent Perronnin
发明人： Sandra Skaff , Beilei Xu , Peter Paul , Craig Saunders , Florent Perronnin
IPC分类号： G06K9/00 , G06K9/46 , G06K9/62
CPC分类号： G06K9/00785 , G06K9/00832 , G06N99/005
摘要： A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor/representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.
摘要翻译：用于检测车辆占用违规的系统包括图像捕获模块，其从定位成查看迎面而来的交通的相机获取包括车厢的图像。该系统包括违规判定装置，其包括处理用于确定图像描述符的图像像素的特征提取模块。该过程选自连续平均量化变换; 尺度不变特征变换; 梯度直方图; 一个视觉词汇表示; Fisher矢量表示法以及上述的组合。该系统还包括分类器，其确定车辆图像描述符/表示相对于超平面位于投影特征空间中的距离。分类器确定距离是否满足阈值，并在满足阈值时对图像进行分类。处理器实现模块。图形用户界面输出分类。

9. 发明申请

US20130336538A1 Occupancy detection for managed lane enforcement based on localization and classification of windshield images 有权
标题翻译：基于挡风玻璃图像的本地化和分类的管理车道执行的占用检测
公开(公告)号：US20130336538A1
公开(公告)日：2013-12-19
申请号：US13527228
申请日：2012-06-19
申请人： Sandra Skaff , Beilei Xu , Peter Paul , Craig Saunders , Florent Perronnin
发明人： Sandra Skaff , Beilei Xu , Peter Paul , Craig Saunders , Florent Perronnin
IPC分类号： G06K9/62
CPC分类号： G06K9/00785 , G06K9/00832 , G06N99/005
摘要： A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor/representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.
摘要翻译：用于检测车辆占用违规的系统包括图像捕获模块，其从定位成查看迎面而来的交通的相机获取包括车厢的图像。该系统包括违规判定装置，其包括处理用于确定图像描述符的图像像素的特征提取模块。该过程选自连续平均量化变换; 尺度不变特征变换; 梯度直方图; 一个视觉词汇表示; Fisher矢量表示法以及上述的组合。该系统还包括分类器，其确定车辆图像描述符/表示相对于超平面位于投影特征空间中的距离。分类器确定距离是否满足阈值，并在满足阈值时对图像进行分类。处理器实现模块。图形用户界面输出分类。

10. 发明申请

US20130290222A1 RETRIEVAL SYSTEM AND METHOD LEVERAGING CATEGORY-LEVEL LABELS 有权
标题翻译：检索系统和方法提取类别级标签
公开(公告)号：US20130290222A1
公开(公告)日：2013-10-31
申请号：US13458183
申请日：2012-04-27
申请人： Albert Gordo , José Antonio Rodriguez Serrano , Florent Perronnin
发明人： Albert Gordo , José Antonio Rodriguez Serrano , Florent Perronnin
IPC分类号： G06F17/30 , G06F15/18
CPC分类号： G06F17/30247 , G06K9/6247 , G06K9/6259
摘要： An instance-level retrieval method and system are provided. A representation of a query image is embedded in a multi-dimensional space using a learned projection. The projection is learned using category-labeled training data to optimize a classification rate on the training data. The joint learning of the projection and the classifiers improves the computation of similarity/distance between images by embedding them in a subspace where the similarity computation outputs more accurate results. An input query image can thus be used to retrieve similar instances in a database by computing the comparison measure in the embedding space.
摘要翻译：提供实例级检索方法和系统。使用学习投影将查询图像的表示嵌入到多维空间中。使用类别标记的训练数据学习投影，以优化训练数据的分类率。投影和分类器的联合学习通过将图像嵌入到相似度计算输出更准确的结果的子空间来改善图像之间的相似度/距离的计算。因此，输入查询图像可以用于通过计算嵌入空间中的比较度量来检索数据库中的类似实例。

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