Detecting Doctored JPEG Images
    61.
    发明申请
    Detecting Doctored JPEG Images 有权
    检测Doctored JPEG图像

    公开(公告)号:US20070195106A1

    公开(公告)日:2007-08-23

    申请号:US11276204

    申请日:2006-02-17

    IPC分类号: G09G5/02

    摘要: Systems and methods for detecting doctored JPEG images are described. In one aspect, a JPEG image is evaluated to determine if the JPEG image comprises double quantization effects of double quantized Discrete Cosine Transform coefficients. In response to results of these evaluation operations, the systems and methods determine whether the JPEG image has been doctored and identify any doctored portion.

    摘要翻译: 描述用于检测编码的JPEG图像的系统和方法。 在一个方面,评估JPEG图像以确定JPEG图像是否包括双量化离散余弦变换系数的双量化效应。 响应于这些评估操作的结果,系统和方法确定JPEG图像是否被编辑并识别任何编辑部分。

    Robust online face tracking
    62.
    发明授权
    Robust online face tracking 有权
    强大的在线人脸跟踪

    公开(公告)号:US08098885B2

    公开(公告)日:2012-01-17

    申请号:US11265773

    申请日:2005-11-02

    IPC分类号: G06K9/00

    摘要: Systems and methods are described for robust online face tracking. In one implementation, a system derives multiple resolutions of each video frame of a video sequence portraying movement of a visual object. The system tracks movement of the visual object in a low resolution as input for tracking the visual object in a higher resolution. The system can greatly reduce jitter while maintaining an ability to reliably track fast-moving visual objects.

    摘要翻译: 描述了用于强大的在线人脸跟踪的系统和方法。 在一个实现中,系统导出描绘视觉对象的移动的视频序列的每个视频帧的多个分辨率。 系统以低分辨率跟踪可视对象的移动,作为用于以更高分辨率跟踪视觉对象的输入。 该系统可以大大减少抖动,同时保持可靠地跟踪快速移动的视觉对象的能力。

    Tensor linear laplacian discrimination for feature extraction
    63.
    发明授权
    Tensor linear laplacian discrimination for feature extraction 有权
    特征提取的张量线性拉普拉斯判别

    公开(公告)号:US08024152B2

    公开(公告)日:2011-09-20

    申请号:US12235927

    申请日:2008-09-23

    IPC分类号: G06F17/16 G06F17/11

    CPC分类号: G06F17/30598 G06K9/6234

    摘要: Tensor linear Laplacian discrimination for feature extraction is disclosed. One embodiment comprises generating a contextual distance based sample weight and class weight, calculating a within-class scatter using the at least one sample weight and a between-class scatter for multiple classes of data samples in a sample set using the class weight, performing a mode-k matrix unfolding on scatters and generating at least one orthogonal projection matrix.

    摘要翻译: 公开了用于特征提取的张量线性拉普拉斯判别。 一个实施例包括生成基于上下文距离的样本权重和类权重,使用所述至少一个样本权重来计算类内散度,以及使用类权重在样本集合中的多类数据样本之间进行类间散射,执行 mode-k矩阵在散射上展开并生成至少一个正交投影矩阵。

    HYBRID GRAPH MODEL FOR UNSUPERVISED OBJECT SEGMENTATION
    64.
    发明申请
    HYBRID GRAPH MODEL FOR UNSUPERVISED OBJECT SEGMENTATION 有权
    用于不间断对象分类的混合图形模型

    公开(公告)号:US20110206276A1

    公开(公告)日:2011-08-25

    申请号:US13100891

    申请日:2011-05-04

    IPC分类号: G06K9/34

    摘要: This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

    摘要翻译: 本公开描述了用于无人监督的对象分割的集成框架。 通过以集成的方式使用算法将自上而下的约束和自下而上的对象形状约束集成在一起,进行类无监督对象分割。 该算法描述了对象部分和超像素之间的关系。 该过程通过对象部分形成对象形状,并将像素图像监视到超像素中,该算法与约束相结合。 本公开描述了从混合图计算掩模图,将图像分割成前景对象和背景,以及从背景显示前景对象。

    Method for modeling data structures by creating digraphs through contexual distances
    65.
    发明授权
    Method for modeling data structures by creating digraphs through contexual distances 有权
    通过连续距离创建二维图来建立数据结构的方法

    公开(公告)号:US07970727B2

    公开(公告)日:2011-06-28

    申请号:US12032705

    申请日:2008-02-18

    IPC分类号: G06F17/10

    CPC分类号: G06K9/6248

    摘要: A method for modeling data affinities and data structures. In one implementation, a contextual distance may be calculated between a selected data point in a data sample and a data point in a contextual set of the selected data point. The contextual set may include the selected data point and one or more data points in the neighborhood of the selected data point. The contextual distance may be the difference between the selected data point's contribution to the integrity of the geometric structure of the contextual set and the data point's contribution to the integrity of the geometric structure of the contextual set. The process may be repeated for each data point in the contextual set of the selected data point. The process may be repeated for each selected data point in the data sample. A digraph may be created using a plurality of contextual distances generated by the process.

    摘要翻译: 一种用于建模数据亲和度和数据结构的方法。 在一个实现中,可以在数据样本中的所选数据点和所选数据点的上下文集合中的数据点之间计算上下文距离。 所述上下文集合可以包括所选数据点和所选数据点附近的一个或多个数据点。 上下文距离可以是所选数据点对上下文集合的几何结构的完整性的贡献与数据点对上下文集合的几何结构的完整性的贡献之间的差异。 可以对所选数据点的上下文集合中的每个数据点重复该过程。 可以对数据样本中的每个选定的数据点重复该过程。 可以使用由该过程生成的多个上下文距离来创建有向图。

    Object detection and recognition with bayesian boosting
    66.
    发明授权
    Object detection and recognition with bayesian boosting 有权
    贝叶斯提升对象检测和识别

    公开(公告)号:US07949621B2

    公开(公告)日:2011-05-24

    申请号:US11871899

    申请日:2007-10-12

    申请人: Rong Xiao Xiaoou Tang

    发明人: Rong Xiao Xiaoou Tang

    IPC分类号: G06F15/18

    CPC分类号: G06N7/005 G06K9/6256

    摘要: An efficient, effective and at times superior object detection and/or recognition (ODR) function may be built from a set of Bayesian stumps. Bayesian stumps may be constructed for each feature and object class, and the ODR function may be constructed from the subset of Bayesian stumps that minimize Bayesian error for a particular object class. That is, Bayesian error may be utilized as a feature selection measure for the ODR function. Furthermore, Bayesian stumps may be efficiently implemented as lookup tables with entries corresponding to unequal intervals of feature histograms. Interval widths and entry values may be determined so as to minimize Bayesian error, yielding Bayesian stumps that are optimal in this respect.

    摘要翻译: 可以从一组贝叶斯树桩构建一个有效,有效且有时优越的物体检测和/或识别(ODR)功能。 可以为每个特征和对象类构造贝叶斯树桩,并且可以从贝叶斯树桩的子集构建ODR功能,以使特定对象类的贝叶斯误差最小化。 也就是说,贝叶斯误差可以用作ODR功能的特征选择测量。 此外,贝叶斯树桩可以被有效地实现为具有对应于特征直方图的不等间隔的条目的查找表。 间隔宽度和入口值可以被确定为使贝叶斯误差最小化,从而产生在这方面是最佳的贝叶斯树桩。

    Directed Graph Embedding
    67.
    发明申请
    Directed Graph Embedding 审中-公开
    定向图嵌入

    公开(公告)号:US20100121792A1

    公开(公告)日:2010-05-13

    申请号:US12521985

    申请日:2008-01-07

    IPC分类号: G06N5/02 G06F15/18 G06F7/548

    CPC分类号: G06F16/9024

    摘要: Directed graph embedding is described. In one implementation, a system explores the link structure of a directed graph and embeds the vertices of the directed graph into a vector space while preserving affinities that are present among vertices of the directed graph. Such an embedded vector space facilitates general data analysis of the information in the directed graph. Optimal embedding can be achieved by measuring local affinities among vertices via transition probabilities between the vertices, based on a stationary distribution of Markov random walks through the directed graph. For classifying linked web pages represented by a directed graph, the system can train a support vector machine (SVM) classifier, which can operate in a user-selectable number of dimensions.

    摘要翻译: 描述了定向图嵌入。 在一个实现中,系统探索有向图的链接结构,并将有向图的顶点嵌入到向量空间中,同时保留存在于有向图的顶点之间的亲和度。 这样的嵌入向量空间有助于对有向图中的信息的一般数据分析。 基于通过有向图的马尔科夫随机游走的平稳分布,可以通过顶点之间的转移概率来测量顶点之间的局部亲和度来实现最佳嵌入。 为了对由有向图表示的链接的网页进行分类,系统可以训练支持向量机(SVM)分类器,其可以以用户可选择的维数操作。

    Image-based face search
    68.
    发明授权
    Image-based face search 有权
    基于图像的脸部搜索

    公开(公告)号:US07684651B2

    公开(公告)日:2010-03-23

    申请号:US11466750

    申请日:2006-08-23

    IPC分类号: G06K9/60

    CPC分类号: G06F17/30247

    摘要: A search includes comparing a query image provided by a user to a plurality of stored images of faces stored in a stored image database, and determining a similarity of the query image to the plurality of stored images. One or more resultant images of faces, selected from among the stored images, are displayed to the user based on the determined similarity of the stored images to the query image provided by the user. The resultant images are displayed based at least in part on one or more facial features.

    摘要翻译: 搜索包括将由用户提供的查询图像与存储在存储的图像数据库中的多个存储的面部图像进行比较,以及确定查询图像与多个存储图像的相似性。 基于所确定的存储的图像与由用户提供的查询图像的相似度,向用户显示从所存储的图像中选择的一个或多个所得到的面部图像。 所得图像至少部分地基于一个或多个面部特征显示。

    Joint boosting feature selection for robust face recognition
    69.
    发明授权
    Joint boosting feature selection for robust face recognition 有权
    联合提升功能选择,强大的人脸识别

    公开(公告)号:US07668346B2

    公开(公告)日:2010-02-23

    申请号:US11277098

    申请日:2006-03-21

    申请人: Rong Xiao Xiaoou Tang

    发明人: Rong Xiao Xiaoou Tang

    IPC分类号: G06K9/00

    CPC分类号: G06K9/6256 G06K9/00281

    摘要: Methods and systems are provided for selecting features that will be used to recognize faces. Three-dimensional models are used to synthesize a database of virtual face images. The virtual face images cover wide appearance variations, different poses, different lighting conditions and expression changes. A joint boosting algorithm is used to identify discriminative features by selecting features from the plurality of virtual images such that the identified discriminative features are independent of the other images included in the database.

    摘要翻译: 提供了用于选择将用于识别面部的特征的方法和系统。 三维模型用于合成虚拟脸部图像的数据库。 虚拟脸部图像涵盖宽的外观变化,不同的姿势,不同的照明条件和表情变化。 联合增强算法用于通过从多个虚拟图像中选择特征来识别识别特征,使得所识别的鉴别特征与包括在数据库中的其它图像无关。

    Adaptive Visual Similarity for Text-Based Image Search Results Re-ranking
    70.
    发明申请
    Adaptive Visual Similarity for Text-Based Image Search Results Re-ranking 审中-公开
    基于文本的图像搜索结果的自适应视觉相似性重新排序

    公开(公告)号:US20090313239A1

    公开(公告)日:2009-12-17

    申请号:US12140244

    申请日:2008-06-16

    申请人: Fang Wen Xiaoou Tang

    发明人: Fang Wen Xiaoou Tang

    IPC分类号: G06F17/30

    摘要: Described is a technology in which images initially ranked by some relevance estimate (e.g., according to text-based similarities) are re-ranked according to visual similarity with a user-selected image. A user-selected image is received and classified into an intention class, such as a scenery class, portrait class, and so forth. The intention class is used to determine how visual features of other images compare with visual features of the user-selected image. For example, the comparing operation may use different feature weighting depending on which intention class was determined for the user-selected image. The other images are re-ranked based upon their computed similarity to the user-selected image, and returned as query results. Retuning of the feature weights using actual user-provided relevance feedback is also described.

    摘要翻译: 描述了一种技术,其中根据与用户选择的图像的视觉相似性来重新排列根据某些相关性估计(例如,根据基于文本的相似性)排序的图像。 接收用户选择的图像并将其分类为意图类别,例如风景类别,肖像类别等。 意图类用于确定其他图像的视觉特征如何与用户选择的图像的视觉特征进行比较。 例如,比较操作可以根据为用户选择的图像确定哪种意图类别而使用不同的特征加权。 其他图像根据其计算出的与用户选择的图像的相似度重新排列,并作为查询结果返回。 还描述了使用实际的用户提供的相关性反馈来重新调整特征权重。