会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 83. 发明授权
    • Automated method and system for naming documents from a scanned source based on manually marked text
    • 自动方法和系统,用于根据手动标记的文本从扫描的源中命名文档
    • US08285047B2
    • 2012-10-09
    • US11866913
    • 2007-10-03
    • Ramesh NagarajanMatthew John Nolepa
    • Ramesh NagarajanMatthew John Nolepa
    • G06K9/00
    • G06K9/2063G06K2209/01
    • A method for associating text with image data of documents is herein described. The method includes receiving image data of a document with manually marked text and recognizing the manually marked text. The image data is then annotated (e.g., tagged) using the manually marked text and the image data of the document is stored. When manually marked text is recognized, recognized text may be generated for annotating the image data of the document and used to populate a field associated with the image data. The field may be a name of the document or a subject line of an e-mail message, for example. A method including identifying the location of manually marked text in a first scanned document to automatically identify and annotate text in a corresponding location in a second scanned document is also disclosed.
    • 这里描述用于将文本与文档的图像数据相关联的方法。 该方法包括用手动标记的文本接收文档的图像数据并识别手动标记的文本。 然后使用手动标记的文本对图像数据进行注释(例如,标记),并存储文档的图像数据。 当识别到手动标记的文本时,可以生成识别的文本以注释文档的图像数据并用于填充与图像数据相关联的字段。 例如,该字段可以是电子邮件消息的文档的名称或主题行。 还公开了一种方法,其包括在第一扫描文档中识别手动标记的文本的位置以自动识别和注释第二扫描文档中相应位置中的文本。
    • 84. 发明授权
    • Resizing a digital document image via background content removal
    • 通过背景内容删除调整数字文档图像的大小
    • US08274533B2
    • 2012-09-25
    • US12369790
    • 2009-02-12
    • Claude S. FillionVishal MongaZhigang FanRamesh Nagarajan
    • Claude S. FillionVishal MongaZhigang FanRamesh Nagarajan
    • G09G5/02
    • G06T3/0012
    • What is disclosed is a system and method for performing a background deletion that exploits both local and global context to remove background and other white space between objects with the aim of retaining structural relationships between objects in the document. A document image is received and seams are carved through the image. Seams composed of uniform background pixels are identified. Adjacent seams containing background pixels are collected into groups of seams. The background seam groups are classified according to their widths. A target number of seams to be removed for each background seam group is then determined based on the classification. Seam groups which are wider will have at least the same or a greater target number of seams to be deleted therefrom than will seam groups of narrower widths. The document image is then resized by deleting seams from the seam groups based on the assigned target number.
    • 公开的是用于执行背景删除的系统和方法,其利用本地和全局上下文来移除对象之间的背景和其他空白空间,目的是保留文档中的对象之间的结构关系。 收到文件图像,并通过图像刻成接缝。 识别由均匀背景像素构成的接缝。 包含背景像素的相邻接缝被收集成一组接缝。 背景缝组根据其宽度进行分类。 然后基于分类确定要为每个背景接缝组去除的目标接缝数目。 与较窄宽度的接缝组相比,更宽的接缝组将具有至少相同或更大的目标数量的接缝。 然后通过基于分配的目标号码从接缝组中删除接缝来调整文档图像的大小。
    • 85. 发明授权
    • Iterative selection of pixel paths for content aware image resizing
    • 用于内容感知图像调整大小的像素路径的迭代选择
    • US08270771B2
    • 2012-09-18
    • US12330879
    • 2008-12-09
    • Claude S. FillionVishal MongaRamesh Nagarajan
    • Claude S. FillionVishal MongaRamesh Nagarajan
    • G06K9/32G06K9/36G06K15/10G09G5/00G09G5/02H04N5/44H04N9/74H04N3/223H04N1/393
    • G06T3/00
    • What is disclosed is a method for iterative seam selection in an image resizing system utilizing a seam carving technique. In one embodiment, an importance map is generated for a received source image. Seams are carved through the image from one edge to an opposite edge. An energy is computed for each seam based on pixel importance values. A distance is computed from each seam to a previously selected seam. A weighting for each seam is computed using a defined weighting function and the calculated seam distances. The weighting is applied to the energy of each seam produce a revised energy for each seam. A seam is selected based on the produced revised energy. The image is resized at a location of the selected seam. The process repeats until the image has been resized to a desired target output dimension. In such a manner, unnatural image resizing results are avoided.
    • 公开的是一种利用接缝雕刻技术的图像调整系统中迭代缝选择的方法。 在一个实施例中,为接收的源图像生成重要性图。 接缝通过图像从一个边缘到另一个边缘被雕刻。 基于像素重要性值计算每个接缝的能量。 从每个接缝到先前选择的接缝计算距离。 使用定义的加权函数和计算的接缝距离来计算每个接缝的加权。 权重应用于每个接缝的能量产生每个接缝的修正能量。 根据产生的修正能量选择接缝。 图像在所选缝的位置被调整大小。 该过程重复,直到图像被调整到期望的目标输出尺寸。 以这种方式,避免了不自然的图像调整结果。
    • 89. 发明授权
    • System and method for replacing binary level masks in a page description
    • 用于在页面描述中替换二进制级掩码的系统和方法
    • US07952753B2
    • 2011-05-31
    • US11518160
    • 2006-09-11
    • Yingjun BaiRamesh Nagarajan
    • Yingjun BaiRamesh Nagarajan
    • G06F15/00
    • G06K15/02G06K15/1825G06K15/1849
    • A system and method for rendering an image file for outputting a copy of an image represented by the image file. In some embodiments, rendering the image includes generating an output file, such as an output bitmap based on a predetermined halftone. In one embodiment, the system comprises an input module, and a processor. The input module obtains a page description of the image to be output. In some instances, the page description includes one or more level masks designed to impart corresponding transparency levels to one or more objects in the page description. The processor (i) detects the one or more level masks in the page description, (ii) determines the one or more corresponding transparency levels of the one or more detected level masks, (iii) obtains one or more custom masks that correspond to the same one or more transparency levels as the one or more detected level masks, wherein the one or more custom masks are designed based on the predetermined halftone, and (iv) replaces the one or more level masks in the page description with the corresponding one or more custom masks.
    • 一种用于呈现用于输出由图像文件表示的图像的副本的图像文件的系统和方法。 在一些实施例中,渲染图像包括基于预定的半色调生成诸如输出位图之类的输出文件。 在一个实施例中,系统包括输入模块和处理器。 输入模块获得要输出的图像的页面描述。 在一些情况下,页面描述包括设计成将相应的透明度级别赋予页面描述中的一个或多个对象的一个​​或多个级别掩码。 处理器(i)检测页面描述中的一个或多个级别掩码,(ii)确定一个或多个检测到的级别掩码的一个或多个相应的透明度级别,(iii)获得一个或多个对应于 与一个或多个检测到的级别掩模相同的一个或多个透明度级别,其中基于预定的半色调设计一个或多个自定义掩码,以及(iv)用页面描述中的一个或多个级别掩码替换相应的一个或多个 更多自定义面具。
    • 90. 发明授权
    • Automatic maintenance of a distributed source tree (DST) network
    • 自动维护分布式源树(DST)网络
    • US07778204B2
    • 2010-08-17
    • US12179872
    • 2008-07-25
    • Thomas P. ChuRamesh NagarajanYung-Terng Wang
    • Thomas P. ChuRamesh NagarajanYung-Terng Wang
    • H04L12/28
    • H04L41/12
    • In one embodiment, an automatically maintained, distributed source tree (DST) network has a plurality of fully connected internal nodes. One or more internal nodes may be connected to one or more external nodes. A first internal node synchronizes its link-state database with another internal node by sending and receiving respective Reduced Sequence Number Packet-Data-Units (PDUs) (RSNPs). An RSNP includes summary information for link-state packets (LSPs) (1) originated by the first internal node, (2) received by the first internal node from the other internal node, and (3) received from and/or originated by external nodes. If an internal link fails, then the corresponding end-nodes may recover and maintain automatic DST operation by entering either relay-mode or switch-mode operation. In relay-mode operation, an end-node tunnels packets to the other end-node via an intermediary node. In switch-mode operation, an intermediary node is selected to forward packets from one end-node to the other end-node.
    • 在一个实施例中,自动维护的分布式源树(DST)网络具有多个完全连接的内部节点。 一个或多个内部节点可以连接到一个或多个外部节点。 第一内部节点通过发送和接收相应的减少序列号分组数据单元(PDU)(RSNP)来将其链路状态数据库与另一内部节点同步。 RSNP包括由第一内部节点发起的链路状态分组(LSP)(1),(2)由第一内部节点从另一个内部节点接收的摘要信息,以及(3)从外部接收和/或发起的 节点。 如果内部链路发生故障,则相应的终端节点可以通过进入中继模式或切换模式操作来恢复和维护自动DST操作。 在中继模式操作中,终端节点经由中间节点将分组隧道传送到另一终端节点。 在交换模式操作中,选择中间节点将分组从一个终端节点转发到另一个终端节点。