Image enhancement through discrete patch optimization

    公开(公告)号:US08571349B1

    公开(公告)日:2013-10-29

    申请号:US13619624

    申请日:2012-09-14

    IPC分类号: G06K9/36

    CPC分类号: G06T7/33

    摘要: An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.

    Video content analysis for automatic demographics recognition of users and videos
    2.
    发明授权
    Video content analysis for automatic demographics recognition of users and videos 有权
    用于用户和视频的自动人口统计识别的视频内容分析

    公开(公告)号:US08924993B1

    公开(公告)日:2014-12-30

    申请号:US13294156

    申请日:2011-11-10

    IPC分类号: H04H60/33

    摘要: A demographics analysis trains classifier models for predicting demographic attribute values of videos and users not already having known demographics.In one embodiment, the demographics analysis system trains classifier models for predicting demographics of videos using video features such as demographics of video uploaders, textual metadata, and/or audiovisual content of videos.In one embodiment, the demographics analysis system trains classifier models for predicting demographics of users (e.g., anonymous users) using user features based on prior video viewing periods of users. For example, viewing-period based user features can include individual viewing period statistics such as total videos viewed. Further, the viewing-period based features can include distributions of values over the viewing period, such as distributions in demographic attribute values of video uploaders, and/or distributions of viewings over hours of the day, days of the week, and the like.

    摘要翻译: 人口统计学分析训练分类器模型,用于预测未知人口统计信息的视频和用户的人口特性值。 在一个实施例中,人口统计分析系统训练分类器模型,以使用诸如视频上传者的人口统计学,文本元数据和/或视频的视听内容的视频特征来预测视频的人口统计。 在一个实施例中,人口统计分析系统训练分类器模型,以基于用户的先前视频观看时段使用用户特征来预测用户(例如,匿名用户)的人口统计。 例如,基于观看期的用户特征可以包括个体观看期间统计,例如观看的总视频。 此外,基于观看期间的特征可以包括在观看期间的值的分布,诸如视频上传者的人口统计属性值中的分布,和/或一天中的几天,星期几等的观看次数分布。

    Using curve invariants to automatically characterize videos
    3.
    发明授权
    Using curve invariants to automatically characterize videos 有权
    使用曲线不变量自动表征视频

    公开(公告)号:US08229156B1

    公开(公告)日:2012-07-24

    申请号:US11500676

    申请日:2006-08-08

    申请人: Jay N. Yagnik

    发明人: Jay N. Yagnik

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00744

    摘要: One embodiment of the present invention provides a computer-based system that automatically characterizes a video. During operation, the system extracts feature vectors from sampled frames in the video. Next, the system uses the extracted feature vectors for successive sampled frames in the video to define a curve. The system then determines a set of invariants for the curve. Next, the system using the set of invariants to characterize the video. The system can then use the characterization of the video to perform various operations, such as classifying the video with respect to other videos or detecting duplicates of the video.

    摘要翻译: 本发明的一个实施例提供一种自动表征视频的基于计算机的系统。 在操作期间,系统从视频中的采样帧中提取特征向量。 接下来,系统使用提取的特征向量用于视频中的连续采样帧来定义曲线。 然后系统确定一组曲线的不变量。 接下来,系统使用一组不变量来表征视频。 然后,系统可以使用视频的表征来执行各种操作,例如对视频进行相对于其他视频分类或检测视频的重复。

    Method and apparatus for automatically summarizing video
    4.
    发明授权
    Method and apparatus for automatically summarizing video 有权
    自动汇总视频的方法和装置

    公开(公告)号:US08699806B2

    公开(公告)日:2014-04-15

    申请号:US11454386

    申请日:2006-06-15

    申请人: Jay N. Yagnik

    发明人: Jay N. Yagnik

    IPC分类号: G06K9/36 G06F3/00

    摘要: One embodiment of the present invention provides a system that automatically produces a summary of a video. During operation, the system partitions the video into scenes and then determines similarities between the scenes. Next, the system selects representative scenes from the video based on the determined similarities, and combines the selected scenes to produce the summary for the video.

    摘要翻译: 本发明的一个实施例提供一种自动产生视频摘要的系统。 在操作期间,系统将视频划分为场景,然后确定场景之间的相似性。 接下来,系统基于确定的相似度从视频中选择代表性场景,并且组合所选择的场景以产生视频的摘要。

    Method and apparatus for automatically annotating images
    5.
    发明申请
    Method and apparatus for automatically annotating images 有权
    自动注释图像的方法和装置

    公开(公告)号:US20080021928A1

    公开(公告)日:2008-01-24

    申请号:US11492485

    申请日:2006-07-24

    申请人: Jay N. Yagnik

    发明人: Jay N. Yagnik

    IPC分类号: G06F17/00

    CPC分类号: G06F17/241 G06K9/00664

    摘要: One embodiment of the present invention provides a system that automatically annotates an image. During operation, the system receives the image. Next, the system extracts image features from the image. The system then identifies other images which have similar image features. The system next obtains text associated with the other images, and identifies intersecting keywords in the obtained text. Finally, the system annotates the image with the intersecting keywords.

    摘要翻译: 本发明的一个实施例提供一种自动注释图像的系统。 在操作期间,系统接收图像。 接下来,系统从图像中提取图像特征。 然后系统识别具有相似图像特征的其他图像。 系统接下来获得与其他图像相关联的文本,并在获取的文本中标识相交的关键字。 最后,系统用相交关键字对图像进行注释。

    Method and apparatus for automatically annotating images
    6.
    发明授权
    Method and apparatus for automatically annotating images 有权
    自动注释图像的方法和装置

    公开(公告)号:US08065313B2

    公开(公告)日:2011-11-22

    申请号:US11492485

    申请日:2006-07-24

    申请人: Jay N. Yagnik

    发明人: Jay N. Yagnik

    CPC分类号: G06F17/241 G06K9/00664

    摘要: One embodiment of the present invention provides a system that automatically annotates an image. During operation, the system receives the image. Next, the system extracts image features from the image. The system then identifies other images which have similar image features. The system next obtains text associated with the other images, and identifies intersecting keywords in the obtained text. Finally, the system annotates the image with the intersecting keywords.

    摘要翻译: 本发明的一个实施例提供一种自动注释图像的系统。 在操作期间,系统接收图像。 接下来,系统从图像中提取图像特征。 然后系统识别具有相似图像特征的其他图像。 系统接下来获得与其他图像相关联的文本,并在获取的文本中标识相交的关键字。 最后,系统用相交关键字对图像进行注释。

    Method and apparatus for automatically summarizing video
    7.
    发明申请
    Method and apparatus for automatically summarizing video 有权
    自动汇总视频的方法和装置

    公开(公告)号:US20070245242A1

    公开(公告)日:2007-10-18

    申请号:US11454386

    申请日:2006-06-15

    申请人: Jay N. Yagnik

    发明人: Jay N. Yagnik

    IPC分类号: G06K9/36

    摘要: One embodiment of the present invention provides a system that automatically produces a summary of a video. During operation, the system partitions the video into scenes and then determines similarities between the scenes. Next, the system selects representative scenes from the video based on the determined similarities, and combines the selected scenes to produce the summary for the video.

    摘要翻译: 本发明的一个实施例提供一种自动产生视频摘要的系统。 在操作期间,系统将视频划分为场景,然后确定场景之间的相似性。 接下来,系统基于确定的相似度从视频中选择代表性场景,并且组合所选择的场景以产生视频的摘要。