-
公开(公告)号：US07933454B2
公开(公告)日：2011-04-26
申请号：US11767739
申请日：2007-06-25
CPC分类号： G06K9/00456 , G06T5/00 , G06T2207/20008
摘要： A method for image enhancement includes providing for a semantic class to be assigned to a digital image based on image content, the assigned semantic class being selected from a plurality of semantic classes. The method further includes providing for an aesthetic enhancement to be applied to the image based on image quality of the image and the assigned semantic class, the enhancement including at least one enhancement dimension selected from a plurality of enhancement dimensions.
摘要翻译： 一种用于图像增强的方法包括：基于图像内容提供要分配给数字图像的语义类，从多个语义类中选择所分配的语义类。 该方法还包括提供基于图像的图像质量和分配的语义类别来应用于图像的美学增强，该增强包括从多个增强维度中选择的至少一个增强维度。
-
公开(公告)号：US20080317358A1
公开(公告)日：2008-12-25
申请号：US11767739
申请日：2007-06-25
CPC分类号： G06K9/00456 , G06T5/00 , G06T2207/20008
摘要： A method for image enhancement includes providing for a semantic class to be assigned to a digital image based on image content, the assigned semantic class being selected from a plurality of semantic classes. The method further includes providing for an aesthetic enhancement to be applied to the image based on image quality of the image and the assigned semantic class, the enhancement including at least one enhancement dimension selected from a plurality of enhancement dimensions.
摘要翻译： 一种用于图像增强的方法包括：基于图像内容提供要分配给数字图像的语义类，从多个语义类中选择所分配的语义类。 该方法还包括提供基于图像的图像质量和分配的语义类别来应用于图像的美学增强，该增强包括从多个增强维度中选择的至少一个增强维度。
-
3.发明授权Method and apparatus for automatically combining a digital image with text data 有权用于自动将数字图像与文本数据组合的方法和装置公开(公告)号：US07457467B2
公开(公告)日：2008-11-25
申请号：US10767348
申请日：2004-01-30
IPC分类号： G06K9/62
CPC分类号： G06F17/30256 , G06K9/00664
摘要： A digital image is automatically combined with text data by automatically classifying the image according to a predetermined set of categories, and automatically selecting text data from a repository, wherein the selected text data match the category of the image according to a predetermined criterion.
摘要翻译： 通过根据预定类别自动分类图像并自动从储存库中选择文本数据，数字图像自动与文本数据组合，其中所选择的文本数据根据预定标准与图像类别匹配。
-
公开(公告)号：US20110184950A1
公开(公告)日：2011-07-28
申请号：US12693795
申请日：2010-01-26
申请人： Sandra SKAFF , Luca Marchesotti , Tommaso Colombino , Ana Fucs , Gabriela Csurka , Yanal Wazaefi , Marco Bressan
发明人： Sandra SKAFF , Luca Marchesotti , Tommaso Colombino , Ana Fucs , Gabriela Csurka , Yanal Wazaefi , Marco Bressan
CPC分类号： G06F17/30265 , G06F17/30274 , G06K9/00664 , G06N99/005
摘要： A system and method for assisting a user in navigation of an image dataset are disclosed. The method includes receiving a user's text query, retrieving images responsive to the query from an image dataset, providing for receiving the user's selection of a first feature selected from a set of available first features via a graphical user interface, providing for receiving the user's selection of a second feature selected from a set of available second features different from the first features via the graphical user interface, and displaying at least some of the retrieved images on the graphical user interface. The displayed images are arranged, e.g., grouped, according to levels and/or combinations of levels of the user-selected first and second features.
摘要翻译： 公开了一种用于辅助用户导航图像数据集的系统和方法。 该方法包括接收用户的文本查询，响应于来自图像数据集的查询检索图像，提供经由图形用户界面接收用户对从一组可用的第一特征中选出的第一特征的选择，提供接收用户的选择 通过图形用户界面从不同于第一特征的一组可用的第二特征选择的第二特征，以及在图形用户界面上显示至少一些所检索的图像。 显示的图像根据用户选择的第一和第二特征的等级和/或组合的级别和/或组合来排列，例如分组。
-
公开(公告)号：US08775424B2
公开(公告)日：2014-07-08
申请号：US12693795
申请日：2010-01-26
申请人： Sandra Skaff , Luca Marchesotti , Tommaso Colombino , Ana Fucs , Gabriela Csurka , Yanal Wazaefi , Marco Bressan
发明人： Sandra Skaff , Luca Marchesotti , Tommaso Colombino , Ana Fucs , Gabriela Csurka , Yanal Wazaefi , Marco Bressan
IPC分类号： G06F17/30
CPC分类号： G06F17/30265 , G06F17/30274 , G06K9/00664 , G06N99/005
摘要： A system and method for assisting a user in navigation of an image dataset are disclosed. The method includes receiving a user's text query, retrieving images responsive to the query from an image dataset, providing for receiving the user's selection of a first feature selected from a set of available first features via a graphical user interface, providing for receiving the user's selection of a second feature selected from a set of available second features different from the first features via the graphical user interface, and displaying at least some of the retrieved images on the graphical user interface. The displayed images are arranged, e.g., grouped, according to levels and/or combinations of levels of the user-selected first and second features.
摘要翻译： 公开了一种用于辅助用户导航图像数据集的系统和方法。 该方法包括接收用户的文本查询，响应于来自图像数据集的查询检索图像，提供经由图形用户界面接收用户对从一组可用的第一特征中选出的第一特征的选择，提供接收用户的选择 通过图形用户界面从不同于第一特征的一组可用的第二特征选择的第二特征，以及在图形用户界面上显示至少一些所检索的图像。 显示的图像根据用户选择的第一和第二特征的等级和/或组合的级别和/或组合来排列，例如分组。
-
公开(公告)号：US20080284791A1
公开(公告)日：2008-11-20
申请号：US11749807
申请日：2007-05-17
申请人： Marco Bressan , Gabriela Csurka
发明人： Marco Bressan , Gabriela Csurka
CPC分类号： G06T11/00 , G06K9/4638 , G06T7/12
摘要： Embodiments herein include a method, service, apparatus, etc., that automatically generates a coloring book image that includes line drawings defining a small number of color coherent, clearly discriminated, closed regions while preserving the basic semantic properties of the original image. These regions hence can be filled in with colored inks, crayons, paints, etc. The method inputs a color image that can be a photograph, scanned image, etc. The method begins by transforming the color image into a chrominance-luminance space and then performs low pass filtering on the color image that preserves the chrominance edges of the features within the color image. Next, the method segments the color image into the features based on locations of the chrominance edges of the features. Then, the method can merge selected features into other features. After performing any merging, the method identifies the remaining chrominance edges of the features within the image and adds lines along the remaining chrominance edges to form outlines of the features. Then, the method automatically filters out all other data from the image to leave only the outlines and produce a revised image consisting of just the outlines. The revised image of just outlines is then output to the user.
摘要翻译： 这里的实施例包括自动生成着色书图像的方法，服务，装置等，其包括定义少量颜色相干，明确区分的封闭区域的线条图，同时保留原始图像的基本语义属性。 这些区域因此可以用彩色油墨，蜡笔，油漆等填充。该方法输入可以是照片，扫描图像等的彩色图像。该方法开始于将彩色图像变换为色度亮度空间，然后 对彩色图像执行低通滤波，以保持彩色图像内的特征的色度边缘。 接下来，该方法基于特征的色度边缘的位置将彩色图像分割成特征。 然后，该方法可以将选定的功能合并成其他功能。 在执行任何合并之后，该方法识别图像内的特征的剩余色度边缘，并沿剩余色度边缘添加线以形成特征轮廓。 然后，该方法自动过滤出图像中的所有其他数据，仅留下轮廓，并生成仅由轮廓组成的修改图像。 然后将简要轮廓的修改后的图像输出给用户。
-
公开(公告)号：US09355337B2
公开(公告)日：2016-05-31
申请号：US12546948
申请日：2009-08-25
CPC分类号： G06K9/6219 , G06K9/00684 , G06K9/527 , G06K9/6292
摘要： Classification of image regions comprises: recursively partitioning an image into a tree of image regions having the image as a tree root and at least one image patch in each leaf image region of the tree, the tree having nodes defined by the image regions and edges defined by pairs of nodes connected by edges of the tree; assigning unary classification potentials to nodes of the tree; assigning pairwise classification potentials to edges of the tree; and labeling the image regions of the tree of image regions based on optimizing an objective function comprising an aggregation of the unary classification potentials and the pairwise classification potentials.
摘要翻译： 图像区域的分类包括：将图像递归地划分为具有树根的图像的图像区域的树和在树的每个叶子图像区域中的至少一个图像块，所述树具有由图像区域定义的节点和限定的边缘 由树的边缘连接的节点对; 将一元分类电位分配给树的节点; 将成对分类电位分配给树的边缘; 以及基于优化包括一元分类电位和成对分类电位的聚集的目标函数来标记图像区域的树的图像区域。
-
公开(公告)号：US08774515B2
公开(公告)日：2014-07-08
申请号：US13090378
申请日：2011-04-20
申请人： Thomas Mensink , Jakob Verbeek , Gabriela Csurka
发明人： Thomas Mensink , Jakob Verbeek , Gabriela Csurka
IPC分类号： G06K9/34
CPC分类号： G06K9/00624 , G06K9/628 , G06K9/6814
摘要： A system and a method are provided for labeling images and for generating an annotation system. The labeling method includes providing a graphical structure, such as a tree structure, which graphically represents predictive correlations between labels in a set of labels. The predictive correlations can, for example, estimate the likelihood, in a training set, that knowing one label has a given value, another label will have a given value. An image to be labeled is received. Feature-based predictions for values of labels in the set of labels are computed for the image. A value for at least one label for the image from the set of labels is computed based on the feature-based label predictions and inference on the structured prediction model.
摘要翻译： 提供了一种用于标记图像和生成注释系统的系统和方法。 标签方法包括提供图形结构，例如树形结构，其以图形方式表示一组标签中的标签之间的预测相关性。 预测相关性可以例如在训练集中估计知道一个标签具有给定值的可能性，另一个标签将具有给定值。 收到要标记的图像。 为图像计算标签集中的标签值的基于特征的预测。 基于基于特征的标签预测和结构化预测模型的推断，计算来自该组标签的图像的至少一个标签的值。
-
9.发明申请SYSTEM AND METHOD FOR OBJECT CLASS LOCALIZATION AND SEMANTIC CLASS BASED IMAGE SEGMENTATION 有权用于对象类定位和基于语义类的图像分割的系统和方法公开(公告)号：US20100040285A1
公开(公告)日：2010-02-18
申请号：US12191579
申请日：2008-08-14
申请人： Gabriela Csurka , Florent Perronnin
发明人： Gabriela Csurka , Florent Perronnin
IPC分类号： G06K9/64
CPC分类号： G06K9/00624 , G06K9/342 , G06K9/4676 , G06T7/11 , G06T2207/10024 , G06T2207/20021 , G06T2207/30236 , G06T2207/30252
摘要： An automated image processing system and method are provided for class-based segmentation of a digital image. The method includes extracting a plurality of patches of an input image. For each patch, at least one feature is extracted. The feature may be a high level feature which is derived from the application of a generative model to a representation of low level feature(s) of the patch. For each patch, and for at least one object class from a set of object classes, a relevance score for the patch, based on the at least one feature, is computed. For at least some or all of the pixels of the image, a relevance score for the at least one object class based on the patch scores is computed. An object class is assigned to each of the pixels based on the computed relevance score for the at least one object class, allowing the image to be segmented and the segments labeled, based on object class.
摘要翻译： 提供了一种用于数字图像的基于分类的分割的自动图像处理系统和方法。 该方法包括提取输入图像的多个片段。 对于每个补丁，至少提取一个要素。 该特征可以是从生成模型的应用导出到补丁的低级特征的表示的高级特征。 对于每个补丁以及来自一组对象类的至少一个对象类，基于至少一个特征来计算补丁的相关性得分。 对于图像的至少一些或全部像素，计算基于补丁得分的至少一个对象类别的相关度得分。 基于所计算的至少一个对象类的相关性分数，将对象类分配给每个像素，允许根据对象类来分割图像和标记的图像。
-
公开(公告)号：US20070140556A1
公开(公告)日：2007-06-21
申请号：US11311991
申请日：2005-12-20
申请人： Jutta Willamowski , Gabriela Csurka
发明人： Jutta Willamowski , Gabriela Csurka
IPC分类号： G06K9/00
CPC分类号： G06K9/0061
摘要： A system suited to correction of red eyes in images includes a detection module which, for a plurality of pixels in a digital image, assigns a probability that a pixel is within a red eye. The probability has a value which may vary from a minimum value to maximum value. A classifier module classifies a patch of the image comprising a region of contiguous pixels which have at least a threshold probability that the pixel is within a red eye. The classifier module distinguishing patches which have a likelihood of including a red eye from other patches which have a likelihood of containing a face or background error rather than a redeye. A correction module assigns a correction to apply to pixels which are in a region of contiguous pixels having at least the threshold probability that the pixel is within a red eye and for which the associated patch has been identified by the classifier as having a probability of including a red eye.
摘要翻译： 适于校正图像中的红眼的系统包括检测模块，对于数字图像中的多个像素，分配像素在红眼内的概率。 概率具有可以从最小值到最大值变化的值。 分类器模块对包括具有像素在红眼内的至少阈值概率的连续像素区域的图像的片段进行分类。 分类器模块区分具有包含来自具有包含脸部或背景错误而不是红眼的可能性的其他斑块的红眼的斑块。 校正模块分配校正以应用于在具有至少阈值概率的连续像素的区域中的像素，该像素在红眼内并且相关联的补丁已被分类器识别为具有包括的概率 红眼。
-
-
-
-
-
-
-
-
-
搜索结果
38 条记录 (耗时 0.026 秒)
