-
公开(公告)号：US08554011B2
公开(公告)日：2013-10-08
申请号：US13155202
申请日：2011-06-07
IPC分类号： G06K9/40
CPC分类号： G06T5/008
摘要： Techniques for automatic exposure correction of images are provided. In particular, the exposure of an input image may be improved by automatically modifying a non-linear function that characterizes the luminance of shadow, mid-tone, and highlight portions of the image. The input image may be segmented into a number of regions and each region is assigned a zone, where the zone indicates a specified range of luminance values. An initial zone assigned to a region of the image may be changed in order to reflect an optimal zone of the region. Based, in part, on the optimal zones for each region of the image, luminance modification parameters may be calculated and applied to the non-linear function in order to produce a modified version of the input image that improves the appearance of overexposed and/or underexposed regions of the input image.
摘要翻译： 提供了图像自动曝光校正技术。 特别地，可以通过自动修改表征图像的阴影，中间色调和高光部分的亮度的非线性函数来改善输入图像的曝光。 输入图像可以被分割成多个区域，并且每个区域被分配一个区域，其中该区域指示指定的亮度值范围。 可以改变分配给图像的区域的初始区域，以便反映该区域的最佳区域。 基于部分地基于图像的每个区域的最佳区域，可以计算亮度修改参数并将其应用于非线性函数，以便产生输入图像的修改版本，其改善曝光过度和/或 输入图像的曝光不足区域。
-
公开(公告)号：US08487187B2
公开(公告)日：2013-07-16
申请号：US12555899
申请日：2009-09-09
IPC分类号： H01B17/30
CPC分类号： H01B17/30 , H01B17/305
摘要： A hermetic feed-through includes a housing body defining a hollow space, a plurality of conductive pins and a seal structure. The plurality of conductive pins extend through the hollow space. The seal structure is provided in the hollow space and includes a single-piece glass component. The single-piece glass component hermetically seals at least two conductive pins to the housing body and electrically insulates the at least two conductive pins from the housing body.
摘要翻译： 密封馈通包括限定中空空间的壳体，多个导电销和密封结构。 多个导电针延伸穿过中空空间。 密封结构设置在中空空间中并且包括单片玻璃部件。 单件式玻璃部件将至少两个导电销气密地密封到壳体主体并将至少两个导电销与壳体主体电绝缘。
-
公开(公告)号：US08452087B2
公开(公告)日：2013-05-28
申请号：US12571317
申请日：2009-09-30
申请人： Jian Sun , Jiangyu Liu
发明人： Jian Sun , Jiangyu Liu
IPC分类号： G06K9/34
CPC分类号： G06T11/60 , G06T7/11 , G06T7/194 , G06T11/001
摘要： Tools disclosed herein comprise progressive, paint stroke based region recognition and selection tools. Using these tools, a user may partially paint a region of interest directly on an image (by using a paint brush or other similar tool). Unlike conventional selection tools, a user is not required to paint the entire region pixel-by-pixel. Rather the desired region is automatically and intelligently recognized based on the partial selection. This is accomplished via a progressive selection algorithm. In addition, these tools provide the ability to quickly execute such region selections on multi-megapixel images.
摘要翻译： 本文公开的工具包括渐进的，基于油漆冲程的区域识别和选择工具。 使用这些工具，用户可以直接在图像上绘制感兴趣的区域（通过使用油漆刷或其他类似的工具）。 与传统的选择工具不同，用户不需要逐个像素地绘制整个区域。 相反，基于部分选择自动和智能地识别期望的区域。 这是通过逐行选择算法实现的。 此外，这些工具还提供了快速执行在百万像素图像上进行这种区域选择的功能。
-
公开(公告)号：US08406564B2
公开(公告)日：2013-03-26
申请号：US12237126
申请日：2008-09-24
申请人： Jian Sun , Heung-Yeung Shum , Lu Yuan , Long Quan
发明人： Jian Sun , Heung-Yeung Shum , Lu Yuan , Long Quan
CPC分类号： G06T5/003 , G06T2207/20016 , G06T2207/20028
摘要： Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.
摘要翻译： 公开了从图像中去除模糊的实施例。 一个公开的实施例提供了一种执行模糊图像的迭代非盲去卷积以形成更新图像的方法。 该方法包括对模糊图像进行下采样以形成包含两个或多个不同分辨率尺度的图像的模糊图像金字塔，对模糊核心进行下采样以形成包含两个或更多个不同大小的粒子的模糊核心金字塔，并且对模糊的所选图像进行解卷积 图像金字塔根据理查森 - 露西反卷积过程，其中采用双边范围/空间滤波器。
-
公开(公告)号：US08386964B2
公开(公告)日：2013-02-26
申请号：US12841094
申请日：2010-07-21
申请人： Jian Sun , Kaiming He , Jiangyu Liu
发明人： Jian Sun , Kaiming He , Jiangyu Liu
CPC分类号： G06T11/00 , G06T7/11 , G06T7/194 , G06T2207/20104
摘要： A user interface enables interactive image matting to be performed on an image The user interface may provide results including an alpha matte as feedback in real time. The user interface may provide interactive tools for selecting a portion of the image, and an unknown region for alpha matte processing may be automatically generated adjacent to the selected region. The user may interactively refine the alpha matte as desired to obtain a satisfactory result.
摘要翻译： 用户界面可以在图像上执行交互式图像遮蔽。用户界面可以提供包括实时反馈的阿尔法无光泽的结果。 用户界面可以提供用于选择图像的一部分的交互式工具，并且可以在与所选择的区域相邻的位置自动生成用于Alpha遮罩处理的未知区域。 用户可根据需要交互地细化α无光泽以获得令人满意的结果。
-
76.发明申请公开(公告)号：US20130004538A1
公开(公告)日：2013-01-03
申请号：US13544129
申请日：2012-07-09
CPC分类号： A61K31/711 , A61K39/39 , A61K2039/55561 , C07H21/04 , C07K14/005 , C12N2740/15022 , C12N2740/16022 , Y02A50/41 , Y02A50/412
摘要： This document relates to compositions and methods for modulating an immune response. For example, compositions of immunostimulatory CpG oligonucleotides derived from retroviral genomes are provided.
-
公开(公告)号：US20120288167A1
公开(公告)日：2012-11-15
申请号：US13107856
申请日：2011-05-13
申请人： Jian Sun , Qi Yin , Xiaoou Tang
发明人： Jian Sun , Qi Yin , Xiaoou Tang
IPC分类号： G06K9/62
CPC分类号： G06K9/00281 , G06K9/00221 , G06K9/00228 , G06K9/00268 , G06K9/00288 , G06K9/42 , G06K9/46 , G06K9/6212 , G06T3/60
摘要： Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations transform at least a portion of an image from a first intrapersonal condition to a second intrapersonal condition to enable more accurate comparison with another image. Some implementations may determine a pose category of an input image and may modify at least a portion of the input image to a different pose category of another image for comparing the input image with the other image. Further, some implementations provide for compression of data representing at least a portion of the input image to decrease the dimensionality of the data.
摘要翻译： 一些实现提供了解决在面部识别期间遇到的内在变化的技术和布置。 例如，一些实施方式将图像的至少一部分从第一内在条件转换为第二内在条件，以使得能够与另一图像更准确地进行比较。 一些实现可以确定输入图像的姿态类别，并且可以将输入图像的至少一部分修改为另一图像的不同姿势类别，以将输入图像与另一图像进行比较。 此外，一些实施方案提供了表示输入图像的至少一部分的数据的压缩以降低数据的维度。
-
公开(公告)号：US20120120097A1
公开(公告)日：2012-05-17
申请号：US12946675
申请日：2010-11-15
申请人： Jian Sun , Ying-Qing Xu , Litian Tao , Mengcheng Huang
发明人： Jian Sun , Ying-Qing Xu , Litian Tao , Mengcheng Huang
CPC分类号： G06F17/30265 , G06T11/001 , G06T11/60
摘要： Techniques for generating a personalized cartoon by using a few text queries are described herein. The present disclosure describes efficiently searching multiple images from a network, obtaining clipart image from the multiple images, and vectorization of the clipart image. The present disclosure also describes techniques to change a style of the cartoon such as recoloring one or more cartoon objects.
摘要翻译： 本文描述了通过使用几个文本查询来生成个性化卡通的技术。 本公开描述了有效地从网络搜索多个图像，从多个图像获得剪贴画图像，以及对剪贴画图像的矢量化。 本公开还描述了改变卡通的风格的技术，例如重新绘制一个或多个卡通对象。
-
公开(公告)号：US20120106853A1
公开(公告)日：2012-05-03
申请号：US12958242
申请日：2010-12-01
申请人： Yue Ma , Justin D. Hamilton , Fang Wen , Jian Sun
发明人： Yue Ma , Justin D. Hamilton , Fang Wen , Jian Sun
IPC分类号： G06K9/68
CPC分类号： G06F17/30268
摘要： Image search techniques are described. In one or more implementations, images in a search result are ordered based at least in part on similarity of the images, one to another. The search result having the ordered images is provided in response to a search request.
摘要翻译： 描述图像搜索技术。 在一个或多个实现中，搜索结果中的图像至少部分地基于图像的相似性而排序。 响应于搜索请求提供具有有序图像的搜索结果。
-
公开(公告)号：US20110060733A1
公开(公告)日：2011-03-10
申请号：US12807217
申请日：2010-08-30
申请人： Sheng Peng , Jian Sun , Lei Hou , Qin Zhang
发明人： Sheng Peng , Jian Sun , Lei Hou , Qin Zhang
IPC分类号： G06F17/30
CPC分类号： G06F17/30867
摘要： An information retrieval method includes pre-processing a set of historical query information and processing a user query. Pre-processing a set of historical query information includes determining a plurality of semantic patterns based on a plurality of queries in the set of historical query information; establishing correspondence relationships between the plurality of semantic patterns and a plurality of filtering and ranking operations. Processing a user query comprises receiving the user query; retrieve a plurality of results in response to the user query; determining a semantic pattern that corresponds to the user query; determining a set of filtering and ranking operations that corresponds to the semantic pattern based on the correspondence relationships; and performing the set of filtering and ranking operations on the plurality of results to generate a set of filtered and ranked results.
摘要翻译： 信息检索方法包括对一组历史查询信息进行预处理并处理用户查询。 预处理一组历史查询信息包括基于该组历史查询信息中的多个查询确定多个语义模式; 建立多个语义模式之间的对应关系和多个过滤和排序操作。 处理用户查询包括接收用户查询; 响应于用户查询检索多个结果; 确定对应于用户查询的语义模式; 基于所述对应关系确定对应于所述语义模式的一组过滤和排序操作; 以及对所述多个结果执行所述一组过滤和排序操作以生成一组过滤和排名结果。
-
-
-
-
-
-
-
-
-
搜索结果
163 条记录 (耗时 0.047 秒)
