专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US07657102B2 System and method for fast on-line learning of transformed hidden Markov models 有权
标题翻译：用于快速在线学习变换隐马尔科夫模型的系统和方法
公开(公告)号：US07657102B2
公开(公告)日：2010-02-02
申请号：US10649382
申请日：2003-08-27
申请人： Nebojsa Jojic , Nemanja Petrovic
发明人： Nebojsa Jojic , Nemanja Petrovic
IPC分类号： G06K9/62 , G10L15/06
CPC分类号： G11B27/28 , G06K9/00711 , G06K9/6297
摘要： A fast variational on-line learning technique for training a transformed hidden Markov model. A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, once the model has been initialized, an expectation-maximization (“EM”) algorithm is used to learn the one or more object class models, so that the video sequence has high marginal probability under the model. In the expectation step (the “E-Step”), the model parameters are assumed to be correct, and for an input image, probabilistic inference is used to fill in the values of the unobserved or hidden variables, e.g., the object class and appearance. In one embodiment of the invention, a Viterbi algorithm and a latent image is employed for this purpose. In the maximization step (the “M-Step”), the model parameters are adjusted using the values of the unobserved variables calculated in the previous E-step.
摘要翻译：一种快速变化的在线学习技术，用于训练变换后的隐马尔可夫模型。提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，一旦模型被初始化，使用期望最大化（“EM”）算法来学习一个或多个对象类模型，使得视频序列在该模型下具有高边际概率。在期望步骤（“E步骤”）中，假设模型参数是正确的，对于输入图像，使用概率推断来填充未观察或隐藏变量的值，例如对象类和出现。在本发明的一个实施例中，为此目的采用维特比算法和潜像。在最大化步骤（“M步骤”）中，使用在先前E步骤中计算的未观察到的变量的值来调整模型参数。

22. 发明授权

US07653705B2 Interactive recording and playback for network conferencing 失效
标题翻译：网络会议的交互式录音和播放
公开(公告)号：US07653705B2
公开(公告)日：2010-01-26
申请号：US11609673
申请日：2006-12-12
申请人： Ananta Gudipaty , Avronil Bhattacharjee , Zheng Ni , Bo Qin , Jeremy Smith , Zhi-Wei Lin , Mingju Zhang , Sumeet Bawa , Aliasgar Haveliwala
发明人： Ananta Gudipaty , Avronil Bhattacharjee , Zheng Ni , Bo Qin , Jeremy Smith , Zhi-Wei Lin , Mingju Zhang , Sumeet Bawa , Aliasgar Haveliwala
IPC分类号： G06F15/16 , G06K9/36
CPC分类号： H04N5/765 , G11B27/034 , G11B27/105 , H04N5/77 , H04N5/775 , H04N7/147 , H04N7/15 , H04N7/155 , H04N21/4335
摘要： The present interactive recording and playback technique provides the ability to archive the content, the discussions and the metadata of a meeting or similar event; then aggregate, search and annotate across this data; and finally edit, combine, or split various recordings to create new presentations. This interactive recording and playback technique provides rich productivity and innovation that is unavailable today.
摘要翻译：本交互式录音和播放技术提供了存档会议或类似事件的内容，讨论和元数据的能力; 然后对这些数据进行聚合，搜索和注释; 最后编辑，组合或分割各种录音以创建新的演示文稿。这种交互式录音和播放技术提供了现在无法实现的丰富的生产力和创新。

23. 发明授权

US07643676B2 System and method for adaptive interpolation of images from patterned sensors 有权
标题翻译：用于图形传感器图像自适应插值的系统和方法
公开(公告)号：US07643676B2
公开(公告)日：2010-01-05
申请号：US11046324
申请日：2005-01-29
申请人： Henrique Malvar
发明人： Henrique Malvar
IPC分类号： G06K9/00
CPC分类号： G06T3/4015
摘要： A adaptive filter interpolation method and system for the demosaicing of color images. In general, input pixels are input in a Bayer-mosaiced pattern (only one color per pixel), and output pixels are in full RGB mode (three color values per pixel). For each pixel location, in raster scan order, the processing steps can be summarized as follows. Following a regular raster scanning order (from left to right and top to bottom), for each pixel location horizontal and vertical gradients are first computed (whose computation depends on the available color for that pixel), and from those the appropriate interpolation filters are chosen from a small set of predetermined filters. Then, the chosen filters are applied to interpolate the missing data.
摘要翻译：一种用于彩色图像去马赛克的自适应滤波器插值方法和系统。通常，输入像素以拜耳镶嵌图案（每像素仅一种颜色）输入，并且输出像素处于完全RGB模式（每像素三个颜色值）。对于每个像素位置，以光栅扫描顺序，处理步骤可以总结如下。按照常规光栅扫描顺序（从左到右和从上到下），对于每个像素位置，首先计算水平和垂直渐变（其计算取决于该像素的可用颜色），并从中选择合适的内插滤波器从一小组预定的过滤器。然后，应用所选择的滤波器来内插丢失的数据。

24. 发明授权

US07613363B2 Image superresolution through edge extraction and contrast enhancement 有权
标题翻译：图像超分辨率通过边缘提取和对比度增强
公开(公告)号：US07613363B2
公开(公告)日：2009-11-03
申请号：US11165525
申请日：2005-06-23
申请人： John Platt , Hugues Hoppe , Erin Renshaw , Adrian Corduneanu
发明人： John Platt , Hugues Hoppe , Erin Renshaw , Adrian Corduneanu
IPC分类号： G06K9/32
CPC分类号： G06T3/4053 , G06T5/002 , G06T5/008 , G06T5/20 , G06T7/13 , G06T7/194 , G06T2207/10016 , G06T2207/20192
摘要： A technique for generating high-resolution bitmaps from low-resolution bitmaps. A low-resolution bitmap is magnified to form a magnified image. Edge detection is performed on the magnified image to find high contrast edges. A plurality of image patches of the magnified image are generated. These images patches are analyzed by performing connected components analysis on each of them using the high contrast edges to produce a plurality of foreground and background decisions determining whether a portion of an image patch is a background or a foreground region. Then the contrast of one or more pixels in each of the plurality of image patches is enhanced based on the foreground and background decisions. Finally, the system and method of the invention combines the luminance of the enhanced output pixels with the color values generated by the magnification algorithm. This produces a high-resolution bitmap from the contrast-enhanced pixels.
摘要翻译：从低分辨率位图生成高分辨率位图的技术。低分辨率位图被放大以形成放大图像。在放大图像上执行边缘检测，以找到高对比度边缘。生成放大图像的多个图像块。通过使用高对比度边缘对它们中的每一个执行连接的分量分析来分析这些图像块，以产生确定图像块的一部分是背景还是前景区域的多个前景和背景决定。然后，基于前景和背景决定增强多个图像块中的每一个中的一个或多个像素的对比度。最后，本发明的系统和方法将增强输出像素的亮度与由放大算法产生的颜色值相结合。这产生了来自对比度增强像素的高分辨率位图。

25. 发明授权

US07567362B2 Effecting gamut operations using boundary line elements 有权
标题翻译：使用边界线元素来实现色域操作
公开(公告)号：US07567362B2
公开(公告)日：2009-07-28
申请号：US11208472
申请日：2005-08-19
申请人： Siu-Kei Tin
发明人： Siu-Kei Tin
IPC分类号： G03F3/08
CPC分类号： H04N1/6058 , H04N1/603
摘要： The present invention provides for a performing a type of gamut operation for a color device given a color input value, the color device being characterized by a gamut boundary comprising a collection of gamut boundary triangles. Boundary line elements are determined that correspond to a subset of the collection of gamut boundary triangles. The subset of the collection of gamut boundary triangles does not include gamut boundary triangles which are unlikely to yield useful results based on the type of gamut operation and the color input value. Each boundary line element represents a line segment defined by an intersection of one of the gamut boundary triangles within the subset of the collection of gamut boundary triangles with a hue plane, and the hue plane is within the gamut boundary and based on the color input value. In addition, a result is determined for the gamut operation using one or more of the determined boundary line elements. Accordingly, a type of gamut operation is performed using a descriptor which represents the gamut boundary of the color device.
摘要翻译：本发明提供了对于给定彩色输入值的彩色设备执行类型的色域操作，该彩色设备的特征在于包括色域边界三角形的集合的色域边界。确定对应于色域边界三角形集合的子集的边界线元素。色域边界三角形集合的子集不包括根据色域操作类型和颜色输入值不太可能产生有用结果的色域边界三角形。每个边界线元素表示由具有色调平面的色域边界三角形集合的子集内的一个色域边界三角形的交点定义的线段，并且色相平面在色域边界内并且基于颜色输入值。此外，使用所确定的边界线元素中的一个或多个来确定用于色域操作的结果。因此，使用表示彩色设备的色域边界的描述符来执行色域操作的类型。

26. 发明授权

US07508419B2 Image exchange with image annotation 有权
标题翻译：图像交换与图像注释
公开(公告)号：US07508419B2
公开(公告)日：2009-03-24
申请号：US11251041
申请日：2005-10-14
申请人： Kentaro Toyama , David Vronay , Padmanabhan Anandan
发明人： Kentaro Toyama , David Vronay , Padmanabhan Anandan
IPC分类号： H04N5/225 , H04N5/232 , H04N5/76 , G06F15/16 , G06F17/30
CPC分类号： H04L67/306 , G06F17/30265 , H04N1/00132 , H04N1/00137 , H04N1/00148 , H04N1/00172 , H04N1/00244 , H04N5/765 , H04N5/77 , H04N5/781 , H04N5/85 , H04N5/907 , H04N5/9201 , Y10S707/99933
摘要： A system and method for providing a peer-to-peer photo-sharing environment. The system includes: manual and automatic photo annotation at the client; periodic client-server synchronization; an index of client photos on a central server or a photo database that is resident on the central server, which is updated by the client-server synchronization function; end-user search functionality to search the centralized index or photo database; and transmission of the relevant photos to the client via an on-line image cache. In one embodiment, one client's new photos are automatically displayed on another client's computer (e.g., via screen saver or another mechanism).
摘要翻译：一种用于提供对等照片共享环境的系统和方法。系统包括：客户端手动和自动照片注释; 定期客户端 - 服务器同步; 在中央服务器上的客户端照片的索引或驻留在中央服务器上的照片数据库，其由客户端 - 服务器同步功能更新; 最终用户搜索功能搜索集中式索引或照片数据库; 以及通过在线图像缓存将相关照片发送到客户端。在一个实施例中，一个客户端的新照片被自动显示在另一个客户端的计算机上（例如，通过屏幕保护程序或其他机构）。

27. 发明授权

US07479957B2 System and method for scalable portrait video 有权
标题翻译：可缩放人像视频的系统和方法
公开(公告)号：US07479957B2
公开(公告)日：2009-01-20
申请号：US11067554
申请日：2005-02-25
申请人： Jiang Li , Keman Yu , Tielin He , Yunfeng Lin , Shipeng Li
发明人： Jiang Li , Keman Yu , Tielin He , Yunfeng Lin , Shipeng Li
IPC分类号： G06T15/00
CPC分类号： H04N21/41407 , H04N7/147 , H04N7/148 , H04N7/173 , H04N19/00 , H04N19/169 , H04N21/234327 , H04N21/4788 , H04N21/6131
摘要： Generation, coding and transmission of an effective video form, scalable portrait video. As an expansion to bi-level video, portrait video is composed of more gray levels, and therefore possesses higher visual quality while it maintains a low bit rate and low computational costs. Portrait video is a scalable video in that each video with a higher level always contains all the information of the video with a lower level. The bandwidths of 2-4 level portrait videos fit into the bandwidth range of 20-40 Kbps that GPRS and CDMA 1X can stably provide. Therefore, portrait video is very promising for video broadcast and communication on 2.5 G wireless networks. With portrait video technology, this system and method is the first to enable two-way video conferencing on Pocket PCs and Handheld PCs.
摘要翻译：生成，编码和传输有效的视频格式，可缩放的肖像视频。作为双级视频的扩展，纵向视频由更多的灰度级组成，因此拥有更高的视觉质量，同时保持较低的比特率和低的计算成本。肖像视频是一个可扩展的视频，每个具有更高级别的视频始终包含具有较低级别的视频的所有信息。 2-4级纵向视频的带宽适应GPRS和CDMA 1X可以稳定提供的20-40 Kbps的带宽范围。因此，肖像视频对于2.5G无线网络的视频广播和通信非常有希望。利用肖像视频技术，该系统和方法是率先在掌上电脑和掌上电脑上实现双向视频会议的方法。

28. 发明授权

US07433490B2 System and method for real time lip synchronization 有权
标题翻译：用于实时唇形同步的系统和方法
公开(公告)号：US07433490B2
公开(公告)日：2008-10-07
申请号：US11435122
申请日：2006-05-16
申请人： Ying Huang , Stephen Ssu-te Lin , Baining Guo , Heung-Yeung Shum
发明人： Ying Huang , Stephen Ssu-te Lin , Baining Guo , Heung-Yeung Shum
IPC分类号： G06K9/00 , G10L15/00
CPC分类号： G06K9/00335 , G10L2021/105
摘要： A novel method for synchronizing the lips of a sketched face to an input voice. The lip synchronization system and method approach is to use training video as much as possible when the input voice is similar to the training voice sequences. Initially, face sequences are clustered from video segments, then by making use of sub-sequence Hidden Markov Models, a correlation between speech signals and face shape sequences is built. From this re-use of video, the discontinuity between two consecutive output faces is decreased and accurate and realistic synthesized animations are obtained. The lip synchronization system and method can synthesize faces from input audio in real-time without noticeable delay. Since acoustic feature data calculated from audio is directly used to drive the system without considering its phonemic representation, the method can adapt to any kind of voice, language or sound.
摘要翻译：一种用于将草绘脸部的嘴唇同步到输入声音的新颖方法。唇部同步系统和方法方法是当输入的声音类似于训练声音序列时尽可能多地使用训练视频。最初，面部序列从视频片段聚类，然后通过利用子序列隐马尔可夫模型，构建了语音信号和面部形状序列之间的相关性。从这种视频的再次使用，两个连续的输出面之间的不连续性被降低，并且获得准确而逼真的合成动画。唇同步系统和方法可以实时地从输入音频合成面部，而没有明显的延迟。由于从音频计算的声学特征数据直接用于驱动系统而不考虑其音位表示，该方法可以适应任何种类的语音，语言或声音。

29. 发明授权

US07343289B2 System and method for audio/video speaker detection 有权
标题翻译：用于音频/视频扬声器检测的系统和方法
公开(公告)号：US07343289B2
公开(公告)日：2008-03-11
申请号：US10606061
申请日：2003-06-25
申请人： Ross Cutler , Ashish Kapoor
发明人： Ross Cutler , Ashish Kapoor
IPC分类号： G10L13/00
CPC分类号： G10L15/25 , G10L25/30 , G10L25/78
摘要： A system and method for detecting speech utilizing audio and video inputs. In one aspect, the invention collects audio data generated from a microphone device. In another aspect, the invention collects video data and processes the data to determine a mouth location for a given speaker. The audio and video are inputted into a time-delay neural network that processes the data to determine which target is speaking. The neural network processing is based upon a correlation to detected mouth movement from the video data and audio sounds detected by the microphone.
摘要翻译：一种利用音频和视频输入来检测语音的系统和方法。一方面，本发明收集从麦克风装置产生的音频数据。在另一方面，本发明收集视频数据并处理数据以确定给定说话者的嘴部位置。音频和视频被输入到时间延迟神经网络中，处理数据以确定哪个目标在说话。神经网络处理基于与从视频数据检测到的嘴部移动和由麦克风检测到的音频声音的相关性。

30. 发明授权

US07337324B2 System and method for non-interactive human answerable challenges 有权
标题翻译：非交互式人为责任挑战的系统和方法
公开(公告)号：US07337324B2
公开(公告)日：2008-02-26
申请号：US10725243
申请日：2003-12-01
申请人： Josh Benaloh , Ismail Cem Paya
发明人： Josh Benaloh , Ismail Cem Paya
IPC分类号： H04L9/32
CPC分类号： H04L63/12 , G06F21/31 , H04L63/0435 , H04L63/0442
摘要： A system and method for automatically determining if a computer user is a human or an automated script. Human interactive proofs (HIPs) are currently used to deter automated registration for web services by automated computer scripts. Unfortunately, HIPs entail multiple steps (request service, receive challenge, respond to challenge) that can be burdensome. The system and method of the invention in one embodiment provides a “black-box” to potential users consisting of a challenge generator and a secret key. The challenge is generated for the user and the response can be provided as part of the service request, eliminating the need for a separate challenge from a service provider and response to the challenge.
摘要翻译：用于自动确定计算机用户是人或自动脚本的系统和方法。人类交互式证明（HIP）目前用于通过自动计算机脚本来阻止Web服务的自动注册。不幸的是，HIP需要多重步骤（请求服务，接收挑战，应对挑战），这可能是繁重的。在一个实施例中，本发明的系统和方法为由挑战发生器和秘密密钥组成的潜在用户提供“黑箱”。为用户生成挑战，并且响应可以作为服务请求的一部分提供，消除了对来自服务提供商的单独挑战的需求以及对挑战的响应。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式