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. 发明申请

US20120141020A1 IMAGE CLASSIFICATION 有权
标题翻译：图像分类
公开(公告)号：US20120141020A1
公开(公告)日：2012-06-07
申请号：US13371719
申请日：2012-02-13
申请人： Gang Hua , Paul Viola
发明人： Gang Hua , Paul Viola
IPC分类号： G06K9/62
CPC分类号： G06F17/3025 , G06F17/30262 , G06K9/00664 , G06K9/4642 , G06K9/4652 , G06K9/6256 , G06K9/6285
摘要： Images are classified as photos (e.g., natural photographs) or graphics (e.g., cartoons, synthetically generated images), such that when searched (online) with a filter, an image database returns images corresponding to the filter criteria (e.g., either photos or graphics will be returned). A set of image statistics pertaining to various visual cues (e.g., color, texture, shape) are identified in classifying the images. These image statistics, combined with pre-tagged image metadata defining an image as either a graphic or a photo, may be used to train a boosting decision tree. The trained boosting decision tree may be used to classify additional images as graphics or photos based on image statistics determined for the additional images.
摘要翻译：图像被分类为照片（例如，自然照片）或图形（例如，漫画，综合生成的图像），使得当用过滤器搜索（在线）时，图像数据库返回与过滤标准相对应的图像（例如，照片或图形将被返回）。在对图像进行分类时，识别关于各种视觉提示（例如，颜色，纹理，形状）的一组图像统计信息。这些图像统计信息与将图像定义为图形或照片的预先标记的图像元数据可以用于训练增强决策树。经训练的增强决策树可以用于基于为附加图像确定的图像统计来将附加图像分类为图形或照片。

22. 发明申请

US20110142299A1 RECOGNITION OF FACES USING PRIOR BEHAVIOR 有权
标题翻译：使用先前的行为识别物质
公开(公告)号：US20110142299A1
公开(公告)日：2011-06-16
申请号：US12637494
申请日：2009-12-14
申请人： Amir Akbarzadeh , Gang Hua
发明人： Amir Akbarzadeh , Gang Hua
IPC分类号： G06K9/00
CPC分类号： G06K9/00288 , G06K9/00677 , G06K9/6212
摘要： Face recognition may be performed using a combination of visual analysis and social context. In one example, a web site such as a social networking site or photo-sharing site allows users to upload photos, and allows faces that appear in the photo to be tagged with users' names. When user A uploads a new photo, two analyses may be performed. First, a face in the photo is compared with known faces of users to determine similarity. Second, it is determined which other users user A frequently uploads photos of. Two probability distributions are created. One distribution assigns high probabilities to users whose photos are similar to the new photo. The other assigns high probabilities to users who frequently appear in photos uploaded by user A. These probability distributions are combined, and the person in the photo is identified as being the person with the highest probability.
摘要翻译：可以使用视觉分析和社会语境的组合来执行面部识别。在一个示例中，诸如社交网站或照片共享网站的网站允许用户上传照片，并且允许照片中出现的脸部被用户的姓名标记。当用户A上传新照片时，可能会执行两次分析。首先，将照片中的脸部与用户的已知脸部进行比较，以确定相似性。其次，确定哪些其他用户A经常上传照片。创建两个概率分布。一个分配对于照片类似于新照片的用户分配高概率。另一方则将频繁出现在用户A上传的照片中的用户分配给高概率。这些概率分布相结合，照片中的人被识别为具有最高概率的人。

23. 发明申请

US20110112012A1 Novel Protein for Binding Bacillus Thuringiensis Cry Toxins and Fragments of Cadherins for Enhancing Cry Toxicity Against Dipterans 审中-公开
标题翻译：用于结合苏云金芽孢杆菌的新型蛋白质用于增强对Dipterans的Cry毒性的卡介素的毒素和片段
公开(公告)号：US20110112012A1
公开(公告)日：2011-05-12
申请号：US12936027
申请日：2009-04-03
申请人： Michael J. Adang , Gang Hua , Mohd Amir Fursan Abdullah , Rui Zhang
发明人： Michael J. Adang , Gang Hua , Mohd Amir Fursan Abdullah , Rui Zhang
IPC分类号： A01N37/18 , A01P7/04 , C07K14/435 , A01H5/00
CPC分类号： A01N63/02 , C07K14/43563 , C07K14/705 , C12N15/8286 , Y02A40/162 , A01N2300/00
摘要： The subject invention relates in part to a novel protein for binding Bacillus thuringiensis Cry toxins, and fragments of cadherins for enhancing Cry toxicity against dipterans. The subject invention also relates in part to the discovery that fragments of a midgut cadherin from a dipteran insect synergize Cry proteins that are active against dipterans. Thus, the subject invention includes the use of fragments of cadherin ectodomains for controlling dipterans. Such fragments (that bind Crys) can be administered to a dipteran insect for ingestion. In some preferred embodiments, the source cadherin is a dipteran cadherin. Also in some preferred embodiments, the fragment is administered with a Cry protein that is active against a dipteran. Variants of the fragments of naturally occurring cadherins are included within the scope of the subject invention.
摘要翻译：本发明部分涉及用于结合苏云金芽孢杆菌Cry毒素的新型蛋白质和用于增强对dip子素的Cry毒性的钙粘蛋白片段。本发明还部分涉及这样一个发现，即来自二极虫昆虫的中肠钙粘蛋白的片段与对dip虫有活性的Cry蛋白协同作用。因此，本发明包括使用钙粘蛋白胞外域的片段来控制dip子。可以将这样的片段（结合Crys）施用于用于摄取的dip虫。在一些优选的实施方案中，源钙粘蛋白是二极体钙粘蛋白。同样在一些优选的实施方案中，所述片段与对dipteran有活性的Cry蛋白施用。天然存在的钙粘素的片段的变体包括在本发明的范围内。

24. 发明授权

US07706610B2 Segmentation of objects by minimizing global-local variational energy 有权
标题翻译：通过最小化全局局部变分能量来分割对象
公开(公告)号：US07706610B2
公开(公告)日：2010-04-27
申请号：US11291309
申请日：2005-11-29
申请人： Zhengyou Zhang , Zicheng Liu , Gang Hua
发明人： Zhengyou Zhang , Zicheng Liu , Gang Hua
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66 , G06K9/48
CPC分类号： G06K9/38 , G06K9/6226 , G06T7/11 , G06T7/143 , G06T7/149 , G06T2207/20116
摘要： An “Image Segmenter” provides a variational energy formulation for segmentation of natural objects from images. In general, the Image Segmenter operates by adopting Gaussian mixture models (GMM) to capture the appearance variation of objects in one or more images. A global image data likelihood potential is then computed and combined with local region potentials to obtain a robust and accurate estimation of pixel foreground and background distributions. Iterative minimization of a “global-local energy function” is then accomplished by evolution of a foreground/background boundary curve by level set, and estimation of a foreground/background model by fixed-point iteration, termed “quasi-semi-supervised EM.” In various embodiments, this process is further improved by providing general object shape information for use in rectifying objects segmented from the image.
摘要翻译： “图像分割器”提供了用于从图像中分割自然对象的变分能量公式。通常，图像分割器通过采用高斯混合模型（GMM）来捕获一个或多个图像中的对象的外观变化来操作。然后计算全局图像数据可能性电位并与局部区域电位组合以获得对像素前景和背景分布的鲁棒且准确的估计。 “全局局部能量函数”的迭代最小化通过水平集演化前景/背景边界曲线，并通过称为“准半监督EM”的定点迭代估计前景/背景模型来实现。 “在各种实施例中，通过提供用于整流从图像分割的对象的一般对象形状信息来进一步改进该过程。

25. 发明申请

US20090252413A1 IMAGE CLASSIFICATION 有权
标题翻译：图像分类
公开(公告)号：US20090252413A1
公开(公告)日：2009-10-08
申请号：US12098026
申请日：2008-04-04
申请人： Gang Hua , Paul Viola
发明人： Gang Hua , Paul Viola
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06F17/3025 , G06F17/30262 , G06K9/00664 , G06K9/4642 , G06K9/4652 , G06K9/6256 , G06K9/6285
摘要： Images are classified as photos (e.g., natural photographs) or graphics (e.g., cartoons, synthetically generated images), such that when searched (online) with a filter, an image database returns images corresponding to the filter criteria (e.g., either photos or graphics will be returned). A set of image statistics pertaining to various visual cues (e.g., color, texture, shape) are identified in classifying the images. These image statistics, combined with pre-tagged image metadata defining an image as either a graphic or a photo, may be used to train a boosting decision tree. The trained boosting decision tree may be used to classify additional images as graphics or photos based on image statistics determined for the additional images.
摘要翻译：图像被分类为照片（例如，自然照片）或图形（例如，漫画，综合生成的图像），使得当用过滤器搜索（在线）时，图像数据库返回与过滤标准相对应的图像（例如，照片或图形将被返回）。在对图像进行分类时，识别关于各种视觉提示（例如，颜色，纹理，形状）的一组图像统计信息。这些图像统计信息与将图像定义为图形或照片的预先标记的图像元数据可以用于训练增强决策树。经训练的增强决策树可以用于基于为附加图像确定的图像统计来将附加图像分类为图形或照片。

26. 发明申请

US20080279423A1 RECOVERING PARAMETERS FROM A SUB-OPTIMAL IMAGE 有权
标题翻译：从子最佳图像恢复参数
公开(公告)号：US20080279423A1
公开(公告)日：2008-11-13
申请号：US11747695
申请日：2007-05-11
申请人： Zhengyou Zhang , Zicheng Liu , Gang Hua , Yang Wang
发明人： Zhengyou Zhang , Zicheng Liu , Gang Hua , Yang Wang
IPC分类号： G06K9/00
CPC分类号： G06K9/00268 , G06K9/4661 , G06T7/11 , G06T2207/30201
摘要： A subregion-based image parameter recovery system and method for recovering image parameters from a single image containing a face taken under sub-optimal illumination conditions. The recovered image parameters (including albedo, illumination, and face geometry) can be used to generate face images under a new lighting environment. The method includes dividing the face in the image into numerous smaller regions, generating an albedo morphable model for each region, and using a Markov Random Fields (MRF)-based framework to model the spatial dependence between neighboring regions. Different types of regions are defined, including saturated, shadow, regular, and occluded regions. Each pixel in the image is classified and assigned to a region based on intensity, and then weighted based on its classification. The method decouples the texture from the geometry and illumination models, and then generates an objective function that is iteratively solved using an energy minimization technique to recover the image parameters.
摘要翻译：一种基于子区域的图像参数恢复系统和方法，用于从包含在次优照明条件下拍摄的面部的单个图像恢复图像参数。恢复的图像参数（包括反照率，照明和脸部几何）可用于在新的照明环境下生成脸部图像。该方法包括将图像中的脸部划分成许多较小的区域，为每个区域生成反照变形模型，并使用基于马尔科夫随机场（MRF）的框架来模拟相邻区域之间的空间依赖关系。定义不同类型的区域，包括饱和，阴影，常规和遮挡区域。将图像中的每个像素分类并分配给基于强度的区域，然后基于其分类进行加权。该方法将纹理与几何和照明模型分离，然后生成使用能量最小化技术迭代求解以恢复图像参数的目标函数。

27. 发明申请

US20080101709A1 SPATIAL SPARSITY INDUCED TEMPORAL PREDICTION FOR VIDEO COMPRESSION 有权
标题翻译：空间分辨率诱导视频压缩的时间预测
公开(公告)号：US20080101709A1
公开(公告)日：2008-05-01
申请号：US11929420
申请日：2007-10-30
申请人： Onur Guleryuz , Gang Hua
发明人： Onur Guleryuz , Gang Hua
IPC分类号： H04N7/50
CPC分类号： H04N19/583 , H04N19/105 , H04N19/117 , H04N19/137 , H04N19/18 , H04N19/196 , H04N19/197 , H04N19/46 , H04N19/48 , H04N19/51 , H04N19/61 , H04N19/82
摘要： A method and apparatus are disclosed herein for spatial sparsity induced temporal prediction. In one embodiment, the method comprises: performing motion compensation to generate a first motion compensated prediction using a first block from a previously coded frame; generating a second motion compensated prediction for a second block to be coded from the first motion compensated prediction using a plurality of predictions in the spatial domain, including generating each of the plurality of predictions by generating block transform coefficients for the first block using a transform, generating predicted transform coefficients of the second block to be coded using the block transform coefficients, and performing an inverse transform on the predicted transform coefficients to create the second motion compensated prediction in the pixel domain; subtracting the second motion compensated prediction from a block in a current frame to produce a residual frame; and coding the residual frame.
摘要翻译：本文公开了一种用于空间稀疏引起的时间预测的方法和装置。在一个实施例中，该方法包括：使用来自先前编码的帧的第一块来执行运动补偿以产生第一运动补偿预测; 使用所述空间域中的多个预测从所述第一运动补偿预测生成要编码的第二块的第二运动补偿预测，包括通过使用变换生成所述第一块的块变换系数来生成所述多个预测中的每一个，使用所述块变换系数生成要编码的所述第二块的预测变换系数，对所述预测变换系数进行逆变换，以生成所述像素域中的所述第二运动补偿预测; 从当前帧中的块中减去第二运动补偿预测以产生残余帧; 并对残余帧进行编码。

28. 发明申请

US20050283857A1 Peptides for inhibiting insects 有权
标题翻译：用于抑制昆虫的肽
公开(公告)号：US20050283857A1
公开(公告)日：2005-12-22
申请号：US11040472
申请日：2005-01-21
申请人： Michael Adang , Gang Hua , Jiang Chen , Mohd Amir Abdullah
发明人： Michael Adang , Gang Hua , Jiang Chen , Mohd Amir Abdullah
IPC分类号： A01N37/18 , A01N63/02 , C07K14/435 , C07K14/705 , C12N15/82
CPC分类号： C12N15/8286 , A01N63/02 , C07K14/705 , Y02A40/162 , A01N2300/00
摘要： The subject invention pertains to the use of peptide fragments of cadherins (including cadherin-like proteins). The subject invention includes a cell (and use thereof) comprising a polynucleotide that expresses the peptide fragment. The subject invention includes methods of feeding the peptides to insects. In preferred embodiments, the peptides are fed to target insects together with one or more insecticidal proteins, preferably (but not limited to) B.t. Cry proteins. When used in this manner, the peptide fragment can not only enhance the apparent toxin activity of the Cry protein against the insect species that was the source of the receptor but also against other insect species. Preferably, the cadherin is a Bacillus thuringiensis (B.t.) insecticidal crystal protein (Cry) toxin receptor. Preferably, the peptide fragment is a binding domain of the receptor. In some preferred embodiments, the peptide is the binding domain nearest to the membrane proximal ectodomain. Corresponding domains are identifiable in a variety of B.t. toxin receptors.
摘要翻译：本发明涉及钙粘蛋白（包括钙粘蛋白样蛋白）的肽片段的用途。本发明包括含有表达肽片段的多核苷酸的细胞（及其用途）。本发明包括将肽喂入昆虫的方法。在优选的实施方案中，将肽与一种或多种杀虫蛋白一起进食至靶昆虫，优选（但不限于）B.t. 哭泣蛋白质当以这种方式使用时，肽片段不仅可以增强Cry蛋白对作为受体来源的昆虫物种的表观毒素活性，而且还可以抵抗其他昆虫物种。优选地，钙粘蛋白是苏云金芽孢杆菌（B.t.）杀虫晶体蛋白（Cry）毒素受体。优选地，肽片段是受体的结合结构域。在一些优选的实施方案中，肽是最接近膜近端胞外域的结合结构域。相应的域可以在各种B.t. 毒素受体。

29. 发明授权

US09952671B2 Method and apparatus for determining motion 有权
公开(公告)号：US09952671B2
公开(公告)日：2018-04-24
申请号：US12902952
申请日：2010-10-12
申请人： Lance Williams , Xiaohui Shen , Gang Hua
发明人： Lance Williams , Xiaohui Shen , Gang Hua
IPC分类号： H04N5/14 , G06F3/01 , G06K9/00 , G06T7/20
CPC分类号： G06F3/017 , G06K9/00355 , G06T7/20
摘要： An apparatus comprising a processor and a memory that cause the apparatus to perform receiving a video indicating a motion, generating a set of scalar representations of movement based, at least in part, on at least part of the video, and identifying at least one predetermined motion that correlates to the set of scalar representations of movement is disclosed.

30. 发明授权

US09240056B2 Video retargeting 有权
标题翻译：视频重新定位
公开(公告)号：US09240056B2
公开(公告)日：2016-01-19
申请号：US12060890
申请日：2008-04-02
申请人： Gang Hua , Cha Zhang , Zhengyou Zhang , Zicheng Liu , Ying Shan
发明人： Gang Hua , Cha Zhang , Zhengyou Zhang , Zicheng Liu , Ying Shan
IPC分类号： H04N7/01 , H04N11/20 , G06K9/20 , G06T11/00 , H04N1/387 , H04N21/2662
CPC分类号： G06T11/00 , H04N1/3875 , H04N7/0122 , H04N21/2662
摘要： Videos are retargeted to a target display for viewing with little to no geometric distortion or video information loss. Salient regions of video frames may be determined using scale-space spatiotemporal information. Video information loss may be a result of spatial loss, due to cropping, and resolution loss, due to resizing. A desired cropping window may be determined using a coarse-to-fine searching strategy. Video frames may be cropped with a window that matches an aspect ratio of the target display, and resized isotropically to match a size of the target display.
摘要翻译：视频被重定向到目标显示器，用于观看几乎没有几何失真或视频信息丢失。可以使用尺度空间时空信息来确定视频帧的显着区域。视频信息丢失可能是由于调整大小而导致的空间损失，由于裁剪和分辨率损失造成的。可以使用粗略到精细的搜索策略来确定期望的裁剪窗口。可以用与目标显示器的纵横比匹配的窗口裁剪视频帧，并且各向同性地调整大小以匹配目标显示器的大小。

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