公开(公告)号：US20120189211A1

公开(公告)日：2012-07-26

申请号：US13010807

申请日：2011-01-21

申请人： Jiebo Luo ,  Wei Liu

发明人： Jiebo Luo ,  Wei Liu

IPC分类号： G06K9/68

CPC分类号： G06K9/6218 ,  G06F17/30247

摘要： A method for searching in a large-scale database of images for images that are visually similar to query images is provided using a processor to perform the following steps: computing visual features for the database images; constructing an Image Anchor Graph that contains a plurality of anchors corresponding to a subset of images in the database, according to the computed visual features; computing visual features for the query images; and retrieving database images similar to one or more user query images using a ranking algorithm that uses the anchors in the Image Anchor Graph according to the computed visual features of both the query images and the database images on the Image Anchor Graph.

摘要翻译： 使用处理器提供用于在视觉上类似于查询图像的图像的大规模数据库中搜索图像的方法，以执行以下步骤：计算数据库图像的视觉特征; 根据所计算出的视觉特征构造图像锚图，所述图像锚图包含与所述数据库中的图像子集对应的多个锚点; 计算查询图像的视觉特征; 以及使用使用图像锚图中的锚点的排序算法来检索类似于一个或多个用户查询图像的数据库图像，所述排序算法根据所计算的图像锚图上的查询图像和数据库图像的视觉特征。

公开(公告)号：US20120182391A1

公开(公告)日：2012-07-19

申请号：US13006674

申请日：2011-01-14

申请人： Andrew Charles Gallagher ,  Jiebo Luo ,  Majid Rabbani

发明人： Andrew Charles Gallagher ,  Jiebo Luo ,  Majid Rabbani

IPC分类号： H04N13/02

CPC分类号： H04N13/221 ,  H04N13/211

摘要： A method of producing a stereo image from a digital video includes receiving a digital video including a plurality of digital images captured by an image capture device; and using a processor to produce stereo suitability scores for at least two digital images from the plurality of digital images. The method further includes selecting a stereo candidate image based on the stereo suitability scores; producing a stereo image from the selected stereo candidate image wherein the stereo image includes the stereo candidate image and an associated stereo companion image based on the plurality of digital images from the digital video; and storing the stereo image whereby the stereo image can be presented for viewing by a user.

摘要翻译： 从数字视频产生立体声图像的方法包括：接收包括由图像捕捉装置拍摄的多个数字图像的数字视频; 以及使用处理器来产生来自所述多个数字图像的至少两个数字图像的立体适应性评分。 该方法还包括：基于立体适应度得分来选择立体候选图像; 从所选择的立体声候选图像中产生立体图像，其中立体图像包括基于来自数字视频的多个数字图像的立体候选图像和相关联的立体声伴随图像; 并且存储立体图像，由此可以呈现立体图像以供用户观看。

公开(公告)号：US08213745B2

公开(公告)日：2012-07-03

申请号：US12576260

申请日：2009-10-09

申请人： Mrityunjay Kumar ,  David D. Conger ,  Jiebo Luo ,  Rodney L. Miller

发明人： Mrityunjay Kumar ,  David D. Conger ,  Jiebo Luo ,  Rodney L. Miller

IPC分类号： G06K9/32 ,  G06K9/36

CPC分类号： G06T3/0012

摘要： A method for modifying an input digital image having input dimensions defined by a number of input rows and input columns to form an output digital image where the number of rows or columns is reduced by one, comprising an image energy map determined from the input image; determining a seam path responsive to the image energy map; imposing constraints on the seam path; and removing pixels along the seam path to modify the input digital image.

摘要翻译： 一种用于修改输入数字图像的方法，该输入数字图像具有由多个输入行和输入列定义的输入尺寸，以形成输出数字图像，其中行或列的数量减1，包括从输入图像确定的图像能量图; 确定响应于所述图像能量图的接缝路径; 对缝线施加约束; 并沿着接缝路径去除像素以修改输入的数字图像。

公开(公告)号：US20120114307A1

公开(公告)日：2012-05-10

申请号：US12942422

申请日：2010-11-09

申请人： Jianchao Yang ,  Jiebo Luo

发明人： Jianchao Yang ,  Jiebo Luo

IPC分类号： H04N5/93

CPC分类号： G06F16/58 ,  G06F16/5838 ,  G06F16/70

摘要： A method for organizing and annotating individual collections of images or videos captured for the same event by different cameras into a master collection, wherein each individual collection forms a media stream in chronological order, includes using a processor to provide the following steps: extracting image features for each image or video of the media stream of each individual collection; analyzing the extracted features to align the media streams in chronological order of the event over a common timeline; transferring annotation from one individual collection to another individual collection based on alignment of the media streams; and storing, displaying or transmitting the transferred annotation.

摘要翻译： 一种用于组织和注释由不同相机捕获的用于相同事件的图像或视频的单个集合到主集合中的方法，其中每个单独集合以时间顺序形成媒体流，包括使用处理器提供以下步骤：提取图像特征 对于每个单独集合的媒体流的每个图像或视频; 分析所提取的特征以使事件的时间顺序在公共时间线上对准媒体流; 基于媒体流的对齐将批注从一个单独的集合转移到另一个集合; 并存储，显示或发送所传送的注释。

公开(公告)号：US20120114296A1

公开(公告)日：2012-05-10

申请号：US12942407

申请日：2010-11-09

申请人： Jiebo Luo ,  Jianchao Yang ,  Jie Yu

发明人： Jiebo Luo ,  Jianchao Yang ,  Jie Yu

IPC分类号： H04N5/77

CPC分类号： H04N9/8205 ,  H04N5/772 ,  H04N5/91

摘要： A method for organizing individual collections of images or videos captured for the same event by different cameras into a master collection, wherein each individual collection forms a media stream in chronological order. A processor for extracting image features for each image or video of the media stream of each collection; constructing a graph based on the extracted features to link the images or videos from the two media streams; finding on the graph at least a pair of images or videos, each from one of the two media streams, that corresponds to correlated captured content; aligning the remaining images or videos in response to the aligned pair so that the all images or videos from the two media streams are aligned over a common timeline; and producing a master stream in chronological order of the event over a common timeline by merging the aligned individual.

摘要翻译： 一种用于将由不同相机拍摄的相同事件的图像或视频的各个集合组织成主集合的方法，其中每个单独集合以时间顺序形成媒体流。 一种用于为每个集合的媒体流的每个图像或视频提取图像特征的处理器; 基于提取的特征构建图表以链接来自两个媒体流的图像或视频; 在图上找到至少一对图像或视频，每个图像或视频各自来自两个媒体流之一，对应于相关的捕获的内容; 响应于对准的对对齐剩余的图像或视频，使得来自两个媒体流的所有图像或视频在公共时间线上对齐; 并通过合并对齐的个体在公共时间轴上按时间顺序生成主流。

公开(公告)号：US07889794B2

公开(公告)日：2011-02-15

申请号：US11346708

申请日：2006-02-03

申请人： Jiebo Luo ,  Christophe E. Papin

发明人： Jiebo Luo ,  Christophe E. Papin

IPC分类号： H04N3/36 ,  H04N5/14

CPC分类号： G11B27/28 ,  G06F17/30811 ,  G06F17/30843 ,  G11B27/105

摘要： A method of analyzing a digital video clip to determine candidate frames for subsequent key frame selection, includes: performing a global motion estimate on the video clip that indicates translation of a scene or camera, or scaling of the scene; and forming a plurality of video segments based on the global motion estimate and labeling each segment in accordance with a predetermined series of camera motion classes. The method further includes extracting key frame candidates from the labeled segments and computing a confidence score for each candidate by using rules corresponding to each camera motion class and a rule corresponding to object motion. An important feature of the invention is that the rules corresponding to camera motion include extracting a candidate frame for a pan segment with a confidence score related to a translation amount during the pan, and not extracting candidate frames for object motion based frames for fast pan and zoom segments, and the rule corresponding to object motion includes extracting a candidate frame for a fixed segment with a confidence score related to the segment length.

摘要翻译： 一种分析数字视频剪辑以确定用于后续关键帧选择的候选帧的方法包括：对指示场景或相机的翻译或场景的缩放的视频剪辑执行全局运动估计; 以及基于全局运动估计形成多个视频片段，并根据预定的一系列相机运动类别对每个片段进行标记。 该方法还包括从标记的片段提取关键帧候选，并通过使用与每个相机运动类别相对应的规则和对应于对象运动的规则来计算每个候选者的置信度分数。 本发明的一个重要特征是与摄像机运动相对应的规则包括在平移期间提取与平移量相关的置信度分数的平移段的候选帧，而不提取用于快盘的基于对象运动的帧的候选帧， 缩放片段，并且与物体运动对应的规则包括以与片段长度相关的置信度得分为固定片段提取候选帧。

公开(公告)号：US07787664B2

公开(公告)日：2010-08-31

申请号：US11392455

申请日：2006-03-29

申请人： Jiebo Luo ,  Phoury Lei

发明人： Jiebo Luo ,  Phoury Lei

IPC分类号： G06K9/00

CPC分类号： G06T11/60 ,  G06K9/00248

摘要： A method for replacing a face in a first digital image with a face from a second digital image including automatically detecting one or more faces in the first digital image; identifying at least one target face from the detected faces that needs to be replaced; automatically detecting one or more faces in the second digital image; identifying at least one source face from the second image detected faces for replacing the target face; using features from the target and source faces to perform facial geometry and appearance corrections to the source face; and replacing the target face with the corrected source face and blending the corrected source face into the first digital image.

摘要翻译： 一种用于从包括自动检测第一数字图像中的一个或多个面部的第二数字图像的面部替换第一数字图像中的面部的方法; 从需要更换的检测到的面识别至少一个目标面; 自动检测第二数字图像中的一个或多个面; 从所述第二图像识别出至少一个源表面，用于替换所述目标面; 使用来自目标和源面的特征来对源面执行面部几何和外观校正; 并用修正的源面代替目标面，并将校正的源面混合到第一数字图像中。

公开(公告)号：US20100171837A1

公开(公告)日：2010-07-08

申请号：US12728467

申请日：2010-03-22

申请人： Bruce H. Pillman ,  Jiebo Luo

发明人： Bruce H. Pillman ,  Jiebo Luo

IPC分类号： H04N17/00

CPC分类号： H04N5/232 ,  G06T7/223 ,  H04N5/23222 ,  H04N5/23245 ,  H04N5/2353

摘要： In a method and digital camera, an initial set of evaluation images are captured. A plurality of characteristics of the initial set of evaluation images are assessed to provide a first assessment. The characteristics include subject motion between the initial set of evaluation images. When the subject motion is in excess of a predetermined threshold, a final capture state of the camera is set responsive to the first assessment. When the subject motion is less than the predetermined threshold, the evaluation images are analyzed to provide analysis results and the final capture state of the camera is set responsive to the first assessment and the analysis results.

摘要翻译： 在方法和数码相机中，捕获初始的评估图像集合。 对初始评估图像集合的多个特征进行评估以提供第一评估。 特征包括初始评估图像集之间的主体运动。 当被摄体动作超过预定阈值时，响应于第一次评估来设置照相机的最终捕获状态。 当对象运动小于预定阈值时，分析评估图像以提供分析结果，并且响应于第一评估和分析结果设置相机的最终捕获状态。

公开(公告)号：US07720288B2

公开(公告)日：2010-05-18

申请号：US11385071

申请日：2006-03-21

申请人： Jiebo Luo ,  Andrew C. Gallagher

发明人： Jiebo Luo ,  Andrew C. Gallagher

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/66 ,  G06K9/36

CPC分类号： G06K9/00

摘要： In a method and system for detecting digital image compositing, a first artifact is detected in an uncompressed digital image. The first artifact is characteristic of an earlier compression of the digital image with a predetermined compression algorithm. An interpolation marker in the image is evaluated to provide interpolation results. During the evaluating, a second artifact of the compression algorithm is counteracted. The image is classified responsive to the interpolation results. The first artifact can be a blocking artifact and the second artifact and interpolation marker can be different periodicities in the image.

摘要翻译： 在用于检测数字图像合成的方法和系统中，在未压缩的数字图像中检测到第一伪像。 第一个工件是使用预定压缩算法对数字图像进行较早压缩的特征。 评估图像中的插值标记以提供插值结果。 在评估期间，抵消了压缩算法的第二个伪像。 根据插值结果对图像进行分类。 第一个工件可以是块伪影，第二个伪像和插值标记可以是图像中不同的周期。

公开(公告)号：US20090257663A1

公开(公告)日：2009-10-15

申请号：US12102395

申请日：2008-04-14

申请人： Jiebo Luo ,  Junsong Yuan

发明人： Jiebo Luo ,  Junsong Yuan

IPC分类号： G06K9/62

CPC分类号： G06F17/30265

摘要： Classification of a group of temporally related images is disclosed, wherein a capture-location sequence is identified from the group of temporally related images. The capture-location-sequence information, which is associated collectively with the capture-location sequence, is compared with each of a plurality of sets of predetermined capture-location-sequence characteristics. Each set is associated with a predetermined classification. An identified classification associated with the group of temporally related images is identified based at least upon results from the comparing step; and the identified classification is stored in a processor-accessible memory system.

摘要翻译： 公开了一组时间相关图像的分类，其中从时间相关图像组识别拍摄位置序列。 将与捕获位置序列一起关联的捕获位置序列信息与多组预定捕获位置序列特征中的每一个进行比较。 每个集合与预定分类相关联。 至少基于比较步骤的结果来识别与时间相关图像组相关联的识别分类; 并且所识别的分类被存储在处理器可访问存储器系统中。