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
    • 71. 发明申请
    • SYSTEM AND METHOD FOR CLASSIFICATION AND RETRIEVAL OF CHINESE-TYPE CHARACTERS AND CHARACTER COMPONENTS
    • 中文字符和字符组成的分类和检索的系统和方法
    • WO2009070615A1
    • 2009-06-04
    • PCT/US2008/084750
    • 2008-11-25
    • CHILD, Warren, Daniel
    • CHILD, Warren, Daniel
    • G06F17/30G06F17/27
    • G06F17/2223G06F17/30265G06F17/30277
    • Recurring components found in Chinese-type characters can be identified and classified by stroke count and free-endpoint count according to embodiments of the present invention. The bidirectional many-to-many relationships between characters and their components can be identified and recorded in electronic or non-electronic format and the recurring components can be ordered and retrieved according to stroke-endpoint value pair. In accordance with an embodiment, bidirectional many-to-many relationships between simple and composite components can be identified and recorded in an electronic or non-electronic format. An embodiment can provide a classification/retrieval method and apparatus for rapid search and retrieval of Chinese-type characters and their components based on stroke-endpoint value pairs and relationships between components and characters.
    • 根据本发明的实施例,可以通过笔画计数和自由终点计数来识别和分类中文字符中发现的重复组分。 可以以电子或非电子格式识别和记录字符及其组件之间的双向多对多关系,并且可以根据笔画 - 端点值对来对循环组件进行排序和检索。 根据实施例,可以以电子或非电子格式来识别和记录简单组件和复合组件之间的双向多对多关系。 一个实施例可以提供一种基于笔画 - 端点值对以及组件和字符之间的关系来快速搜索和检索中文字符及其组件的分类/检索方法和装置。
    • 78. 发明申请
    • 画像検索プログラム
    • 图像搜索程序
    • WO2004047026A1
    • 2004-06-03
    • PCT/JP2002/012135
    • 2002-11-20
    • 富士通株式会社上原 祐介増本 大器椎谷 秀一遠藤 進馬場 孝之
    • 上原 祐介増本 大器椎谷 秀一遠藤 進馬場 孝之
    • G06T7/00
    • G06K9/64G06F17/30247G06F17/30277
    • An image search program includes a feature amount data extraction unit (103) for extracting feature amount data of a plurality of types (such as layout feature amount, texture feature amount, and shape feature amount) from key image data, adaptation judgment unit (104) for judging presence/absence of adaptation depending on whether the similarity calculation is matched with the human similarity sense for the types of the feature amount data extracted by the feature amount data extraction unit (103), a similarity calculation unit (105) for calculating similarity between the key image data and each image data to be searched, according to the result of judgment of the adaptation judgment unit (104), and a search unit (106) for outputting the image data corresponding to the similarity as a search result.
    • 图像搜索程序包括:特征量数据提取单元,用于从关键图像数据中提取多种类型的特征量数据(诸如布局特征量,纹理特征量和形状特征量),适应判断单元(104 ),用于根据相似度计算是否与由特征量数据提取单元(103)提取的特征量数据的类型的人类相似度检验相匹配来判断适应的存在/不存在;相似度计算单元(105),用于计算 根据自适应判断单元(104)的判断结果,关键图像数据和要搜索的每个图像数据之间的相似度,以及用于输出与相似性相对应的图像数据作为搜索结果的搜索单元(106)。
    • 79. 发明申请
    • MEDICAL IMAGE PROCESSING SYSTEMS
    • 医学图像处理系统
    • WO0225588A3
    • 2003-08-28
    • PCT/US0129573
    • 2001-09-21
    • MD ONLINE INCSTEFANESCU DANLEVENTON MICHAEL
    • STEFANESCU DANLEVENTON MICHAEL
    • G06F17/30G06F19/00G06T7/00
    • G06F17/30256G06F17/30277G06F19/321G06F19/3418G06T7/0012G06T7/30G16H50/50
    • The systems described herein employ a pre-processing strategy for image databases to obtain derivative information from images, in particular from within regions of interest (if any) in each image. A similar pre-processing strategy may be applied to a query image so that rapid and highly accurate comparisons may be performed between the query image and images from the image database, based upon the derivative information. The pre-processing strategy may include, for example, normalization of image data, sampling of normalized image data, segmentation of regions of interest, and extraction of feature vectors from the normalized, sampled, segmented image data. The overall strategy may provide for efficacious comparison of new and archived images. Further disclosed herein are techniques employing these strategies in modeling normalized image data for various applications, in organizing and searching databases, in providing a user interface for applying the systems in a medical workplace, and for deploying applications based upon these strategies locally and over computer networks.
    • 本文描述的系统采用图像数据库的预处理策略来从图像中获得衍生信息,特别是从每个图像中的感兴趣区域(如果有的话)获得衍生信息。 类似的预处理策略可以应用于查询图像,使得可以基于导数信息在查询图像和来自图像数据库的图像之间执行快速和高精度的比较。 预处理策略可以包括例如图像数据的归一化,归一化图像数据的采样,感兴趣区域的分割以及从归一化的采样分段图像数据中提取特征向量。 整体策略可能会对新的和归档的图像进行有效的比较。 本文进一步公开的是采用这些策略来建模各种应用的归一化图像数据,组织和搜索数据库,提供用于在医疗工作场所中应用系统的用户界面以及基于这些策略在本地和通过计算机网络部署应用的技术 。
    • 80. 发明申请
    • COMPONENT IMAGERY SYSTEM
    • 组件成像系统
    • WO00068881A2
    • 2000-11-16
    • PCT/US2000/012338
    • 2000-05-05
    • G06F17/30G06T15/50G06T
    • G06T15/506G06F17/30277
    • A large database (10, 11, 114) of digitized background images (12) is provided with one or more attributes (14, 16, 18, 15, 17, 19, 116, 118) associated with each image. Preferably most if not all of the attributes are expressed numerically. The attributes can pertain to lighting conditions at the time the associated photograph was taken, and camera orientation. Such conditions can include the horizontal angle of the primary lighting (H), the vertical angle of the primary lighting (V), a measure of the apparent ground perspective (P), color temperature (CT), a measure of light diffusion (D), a measure of the degree of ambient light (A), and horizontal depth of field focal range boundaries (NF, FF). The database is searchable by one or more of these attributes and/or by subject. A user can select a desired background image and learn the attributes associated with that image. A subject image having matching attributes then can be composited with the background image for a realistic composite montage.
    • 数字化背景图像(12)的大数据库(10,11,114)被提供有与每个图像相关联的一个或多个属性(14,16,18,18,17,19,161,118)。 优选地,大多数(如果不是全部)属性都以数字表示。 这些属性可以与拍摄相关照片时的照明条件和照相机方向有关。 这样的条件可以包括初级照明的水平角(H),初级照明的垂直角(V),表观地面透视度(P),色温(CT),光扩散的测量(D) ),环境光度(A)和水平景深焦距范围边界(NF,FF)的度量。 数据库可以由这些属性和/或主体中的一个或多个来搜索。 用户可以选择所需的背景图像并且学习与该图像相关联的属性。 具有匹配属性的对象图像可以与用于实际的复合蒙太奇的背景图像合成。