公开(公告)号：US06580437B1

公开(公告)日：2003-06-17

申请号：US09602721

申请日：2000-06-26

申请人： Shih-Ping Liou ,  Candemir Toklu ,  Madirakshi Das

发明人： Shih-Ping Liou ,  Candemir Toklu ,  Madirakshi Das

IPC分类号： G06F300

CPC分类号： G06F17/30961 ,  G06F17/3028 ,  G06F17/30796

摘要： A system for organizing digital videos to archive and access them at different levels of abstraction uses data available from a closed-caption text along with off-the-shelf natural language processing tools to segment the video into self-contained story sections and speaker blocks. If the subject changes are marked, the system uses these points to divide the video into distinct stories which are represented as nodes attached to the root node in a tree structure and groups speaker segments belonging to a story under the story node as its children.

摘要翻译： 用于组织数字视频以不同抽象级别对其进行归档和访问的系统使用封闭字幕文本中提供的数据以及现成的自然语言处理工具将视频分割成独立的故事部分和扬声器块。 如果主题变化被标记，则系统使用这些点将视频划分成不同的故事，其被表示为以树结构附接到根节点的节点，并且将属于故事节点下的故事的扬声器分段组合为其子节点。

公开(公告)号：US06278446B1

公开(公告)日：2001-08-21

申请号：US09027637

申请日：1998-02-23

申请人： Shih-Ping Liou ,  Madirakshi Das

发明人： Shih-Ping Liou ,  Madirakshi Das

IPC分类号： G06F300

CPC分类号： G06K9/00711 ,  G06F17/30802 ,  G06F17/30805 ,  G06F17/30852

摘要： A system for interactively organizing and browsing video automatically processes video, creating a video table of contents (VTOC), while providing easy-to-use interfaces for verification, correction, and augmentation of the automatically extracted video structure. Shot detection, shot grouping and VTOC generation are automatically determined without making restrictive assumptions about the structure or content of the video. A nonstationary time series model of difference metrics is used for shot boundary detention. Color and edge similarities are used for shot grouping. Observation about the structure of a wide class of videos are used for the generating the table of contents. The use of automatic processing in conjuction with input from the user provides a meaningful video organization.

摘要翻译： 用于交互式组织和浏览视频的系统自动处理视频，创建视频内容表（VTOC），同时提供易于使用的接口，用于自动提取的视频结构的验证，校正和增加。 自动确定拍摄检测，拍摄分组和VTOC生成，而不对视频的结构或内容做出限制性假设。 不平衡时间序列模型的差异度量用于拍摄边界拘留。 颜色和边缘相似性用于拍摄分组。 观察广泛类视频的结构用于生成目录。 使用与用户输入相结合的自动处理提供了有意义的视频组织。

公开(公告)号：US20130051670A1

公开(公告)日：2013-02-28

申请号：US13221078

申请日：2011-08-30

申请人： Madirakshi Das ,  Alexander C. Loui

发明人： Madirakshi Das ,  Alexander C. Loui

IPC分类号： G06K9/46

CPC分类号： G06K9/6212 ,  G06F17/30056 ,  G06F17/30265

摘要： A method of identifying groups of related digital images in a digital image collection, comprising: analyzing each of the digital images to generate associated feature descriptors related to image content or image capture conditions; storing the feature descriptors associated with the digital images in a metadata database; automatically analyzing the metadata database to identify a plurality of frequent itemsets, wherein each of the frequent itemsets is a co-occurring feature descriptor group that occurs in at least a predefined fraction of the digital images; determining a probability of occurrence for each the identified frequent itemsets; determining a quality score for each of the identified frequent itemsets responsive to the determined probability of occurrence; ranking the frequent itemsets based at least on the determined quality scores; and identifying one or more groups of related digital images corresponding to one or more of the top ranked frequent itemsets.

摘要翻译： 一种在数字图像集合中识别相关数字图像组的方法，包括：分析每个数字图像以生成与图像内容或图像捕获条件相关的相关联的特征描述符; 将与数字图像相关联的特征描述符存储在元数据数据库中; 自动分析所述元数据数据库以识别多个频繁项集，其中所述频繁项集中的每一个是发生在所述数字图像的至少预定义分数中的共同出现的特征描述符组; 确定每个所识别的频繁项集的出现概率; 响应于所确定的发生概率，确定每个所识别的频繁项集的质量得分; 至少基于确定的质量得分对频繁项集进行排序; 以及识别与一个或多个最高排名的频繁项集相对应的一组或多组相关数字图像。

公开(公告)号：US20120213493A1

公开(公告)日：2012-08-23

申请号：US13031347

申请日：2011-02-21

申请人： Jiebo Luo ,  Dhiraj Joshi ,  Peter O. Stubler ,  Madirakshi Das ,  Phoury Lei ,  Vivek Kumar Singh

发明人： Jiebo Luo ,  Dhiraj Joshi ,  Peter O. Stubler ,  Madirakshi Das ,  Phoury Lei ,  Vivek Kumar Singh

IPC分类号： H04N5/93

CPC分类号： H04N9/8205 ,  G06F17/30056 ,  G06F17/30064 ,  G06F17/30274 ,  G06F17/30849 ,  G11B27/105 ,  G11B27/34 ,  H04N5/76 ,  H04N9/8211

摘要： A method for viewing a collection of images or videos, includes analyzing the collection to determine properties of the images or videos and using the determined properties to produce icons corresponding to such properties; providing a time-varying display of the images or videos in the collection following an ordering of the images or videos in the collection and at least one of the corresponding icons; receiving a user selection of an icon; changing the time-varying display of the images or videos in the collection following a reordering of the images or videos in the collection in response to the user selection; storing the sequence of the user selections and associated timing in a script in a processor accessible memory; and playing back the viewing of the collection of images or videos using the script.

摘要翻译： 一种用于查看图像或视频的集合的方法，包括分析所述集合以确定所述图像或视频的属性，并使用所确定的属性来产生与所述属性对应的图标; 在所述集合中的图像或视频的排序和所述对应图标中的至少一个之后提供所述集合中的所述图像或视频的时变显示; 接收用户对图标的选择; 响应于用户选择，在对集合中的图像或视频进行重新排序之后，改变集合中的图像或视频的时变显示; 将用户选择的顺序和关联定时存储在处理器可访问存储器中的脚本中; 并使用该脚本播放图像或视频的收藏。

公开(公告)号：US08122356B2

公开(公告)日：2012-02-21

申请号：US11866636

申请日：2007-10-03

申请人： Joel S. Lawther ,  Cathleen D. Cerosaletti ,  Alexander C. Loui ,  Annette L. Thompson ,  Samuel M. Fryer ,  Edward Covannon ,  Madirakshi Das ,  Dale F. McIntyre ,  Michael J. Telek ,  Stacie L. Hibino

发明人： Joel S. Lawther ,  Cathleen D. Cerosaletti ,  Alexander C. Loui ,  Annette L. Thompson ,  Samuel M. Fryer ,  Edward Covannon ,  Madirakshi Das ,  Dale F. McIntyre ,  Michael J. Telek ,  Stacie L. Hibino

IPC分类号： G06F3/00

CPC分类号： G06F17/30056 ,  G06F3/04817 ,  G06T13/80

摘要： A method for image presentation are provided, in which at least one theme for image presentation is obtained; at least one set of images is acquired for presentation in association with each theme; and a presentation area image is generated for presentation on a display with a plurality of separate presentation objects in the presentation area image; an image value for each of the acquired images is determined; an emphasis score is determined for each of the acquired images. The presentation area image is presented with one of the acquired images in each of the presentation objects; and the presentation objects are animated by moving the presentation objects relative to each other in a manner that attracts more attention to presentation objects that are used to present images having a higher emphasis score than presentation objects that are used to simultaneously present images having a lower emphasis score.

摘要翻译： 提供一种用于图像呈现的方法，其中获得用于图像呈现的至少一个主题; 获取至少一组图像以与每个主题相关联地呈现; 并且生成呈现区域图像以在呈现区域图像中的多个分离的呈现对象的显示器上呈现; 确定每个所获取的图像的图像值; 为每个所获取的图像确定强调分数。 在每个呈现对象中呈现呈现区域图像中的一个获取的图像; 并且呈现对象通过以相对于彼此移动呈现对象的方式来动画化，该方式可以更加注意用于呈现比具有较低强调的图像的呈现对象更高的强调分数的图像的呈现对象 得分了。

公开(公告)号：US20090094518A1

公开(公告)日：2009-04-09

申请号：US11866636

申请日：2007-10-03

申请人： Joel S. Lawther ,  Cathleen D. Cerosaletti ,  Alexander C. Loui ,  Annette L. Thompson ,  Samuel M. Fryer ,  Edward Covannon ,  Madirakshi Das ,  Dale F. Mclntyre ,  Michael J. Telek ,  Stacie L. Hibino

发明人： Joel S. Lawther ,  Cathleen D. Cerosaletti ,  Alexander C. Loui ,  Annette L. Thompson ,  Samuel M. Fryer ,  Edward Covannon ,  Madirakshi Das ,  Dale F. Mclntyre ,  Michael J. Telek ,  Stacie L. Hibino

IPC分类号： G06F3/00

CPC分类号： G06F17/30056 ,  G06F3/04817 ,  G06T13/80

摘要： A method for image presentation are provided, in which at least one theme for image presentation is obtained; at least one set of images is acquired for presentation in association with each theme; and a presentation area image is generated for presentation on a display with a plurality of separate presentation objects in the presentation area image; an image value for each of the acquired images is determined; an emphasis score is determined for each of the acquired images. The presentation area image is presented with one of the acquired images in each of the presentation objects; and the presentation objects are animated by moving the presentation objects relative to each other in a manner that attracts more attention to presentation objects that are used to present images having a higher emphasis score than presentation objects that are used to simultaneously present images having a lower emphasis score.

摘要翻译： 提供一种用于图像呈现的方法，其中获得用于图像呈现的至少一个主题; 获取至少一组图像以与每个主题相关联地呈现; 并且生成呈现区域图像以在呈现区域图像中的多个分离的呈现对象的显示器上呈现; 确定每个所获取的图像的图像值; 为每个所获取的图像确定强调分数。 在每个呈现对象中呈现呈现区域图像中的一个获取的图像; 并且呈现对象通过以相对于彼此移动呈现对象的方式来动画化，该方式可以更加注意用于呈现比具有较低强调的图像的呈现对象更高的强调分数的图像的呈现对象 得分了。

公开(公告)号：US20080002864A1

公开(公告)日：2008-01-03

申请号：US11427352

申请日：2006-06-29

申请人： Madirakshi Das ,  Andrew C. Gallagher ,  Alexander C. Loui

发明人： Madirakshi Das ,  Andrew C. Gallagher ,  Alexander C. Loui

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06K9/00664

摘要： A method of identifying a particular background feature in a digital image, and using such feature to identify images in a collection of digital images that are of interest, includes using the digital image for determining one or more background region(s), with the rest of the image region being the non-background region; analyzing the background region(s) to determine one or more features which are suitable for searching the collection; and using the one or more features to search the collection and identifying those digital images in the collection that have the one or more features.

摘要翻译： 一种识别数字图像中的特定背景特征的方法，并且使用这样的特征来识别感兴趣的数字图像的集合中的图像，包括使用数字图像来确定一个或多个背景区域，其余的 作为非背景区域的图像区域; 分析背景区域以确定适合于搜索收集的一个或多个特征; 以及使用所述一个或多个特征来搜索所述集合并且识别所述集合中具有所述一个或多个特征的那些数字图像。

公开(公告)号：US20060245624A1

公开(公告)日：2006-11-02

申请号：US11116729

申请日：2005-04-28

申请人： Andrew Gallagher ,  Madirakshi Das ,  Peter Stubler

发明人： Andrew Gallagher ,  Madirakshi Das ,  Peter Stubler

IPC分类号： G06K9/00

CPC分类号： G06K9/00288 ,  G06K2009/00322

摘要： A method of identifying at least one particular person of interest in a collection of digital images taken over time, includes providing the collection of digital images with each digital image containing one or more persons; storing in a digital database an appearance model having a set of features that are distance measurements associated with facial features of the particular person of interest at an associated time; and providing an individual recognition classifier that uses the appearance model and the associated time to identify the particular person of interest in images from the collection of digital images.

公开(公告)号：US09218367B2

公开(公告)日：2015-12-22

申请号：US13463183

申请日：2012-05-03

申请人： Madirakshi Das ,  Cathleen D. Cerosaletti ,  Alexander C. Loui

发明人： Madirakshi Das ,  Cathleen D. Cerosaletti ,  Alexander C. Loui

IPC分类号： G06F17/30

CPC分类号： G06F17/30265 ,  G06F17/30551

摘要： The invention relates generally to the field of digital image processing, and in particular to a method for associating and viewing related video and still images. In particular, the present invention is directed to methods for associating and/or viewing digital content records comprising ordering a first set of digital content records and the second set of digital content records based upon information associated with each of the digital content records.

摘要翻译： 本发明一般涉及数字图像处理领域，特别涉及一种用于关联和观看相关视频和静止图像的方法。 特别地，本发明涉及用于关联和/或查看数字内容记录的方法，包括基于与每个数字内容记录相关联的信息来排序第一组数字内容记录和第二组数字内容记录。

公开(公告)号：US08625904B2

公开(公告)日：2014-01-07

申请号：US13221078

申请日：2011-08-30

申请人： Madirakshi Das ,  Alexander C. Loui

发明人： Madirakshi Das ,  Alexander C. Loui

IPC分类号： G06K9/68

CPC分类号： G06K9/6212 ,  G06F17/30056 ,  G06F17/30265

摘要： A method of identifying groups of related digital images in a digital image collection, comprising: analyzing each of the digital images to generate associated feature descriptors related to image content or image capture conditions; storing the feature descriptors associated with the digital images in a metadata database; automatically analyzing the metadata database to identify a plurality of frequent itemsets, wherein each of the frequent itemsets is a co-occurring feature descriptor group that occurs in at least a predefined fraction of the digital images; determining a probability of occurrence for each the identified frequent itemsets; determining a quality score for each of the identified frequent itemsets responsive to the determined probability of occurrence; ranking the frequent itemsets based at least on the determined quality scores; and identifying one or more groups of related digital images corresponding to one or more of the top ranked frequent itemsets.

摘要翻译： 一种在数字图像集合中识别相关数字图像组的方法，包括：分析每个数字图像以生成与图像内容或图像捕获条件相关的相关联的特征描述符; 将与数字图像相关联的特征描述符存储在元数据数据库中; 自动分析元数据数据库以识别多个频繁项集，其中每个频繁项集是在数字图像的至少预定义分数中出现的共同出现的特征描述符组; 确定每个所识别的频繁项集的出现概率; 响应于所确定的发生概率，确定每个所识别的频繁项集的质量得分; 至少基于确定的质量得分对频繁项集进行排序; 以及识别与一个或多个最高排名的频繁项集相对应的一组或多组相关数字图像。