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
    • 1. 发明申请
    • ORTHOGONAL TECHNOLOGY FOR MULTI-LINE CHARACTER RECOGNITION
    • 用于多线字符识别的正交技术
    • WO0210884A3
    • 2002-10-03
    • PCT/US0124015
    • 2001-07-30
    • RAF TECHNOLOGY INCELMENHURST BRIAN J
    • ELMENHURST BRIAN J
    • G06K9/03G06K9/34G06K9/62G06K9/00G05B13/02G06F9/44G06F15/18G06K9/18G06K9/72
    • G06K9/6292G06K9/03G06K9/344G06K2209/01
    • The present invention encompasses a self-orthogonal character recognition engine for executing an iterative method employing a database of predetermined character strings. The method receives a digital representation of a character string (Figure 6). It then generates a proposed result string by applying to the captured digital image a predetermined recognition routine including one or more recognition subroutines. Each recognition subroutine employs an initial parameter setting. Next, if the proposed result string does not match any of the predetermined character strings in the database, the initial parameter setting of a recognition subroutine is changed to a next setting (628, 630). The recognition process is then repeated using the next parameter setting to generate and test a next result string. The process can be repeated iteratively until a result string is verified or the process times out (502, 504, 506, 510).
    • 本发明包括用于执行使用预定字符串的数据库的迭代方法的自正交字符识别引擎。 该方法接收字符串的数字表示(图6)。 然后,通过将捕获的数字图像应用于包括一个或多个识别子程序的预定识别程序来生成提出的结果串。 每个识别子程序都使用初始参数设置。 接下来,如果建议的结果字符串与数据库中的任何预定字符串不匹配,则将识别子例程的初始参数设置改变为下一设置(628,630)。 然后使用下一个参数设置重复识别过程,以生成和测试下一个结果字符串。 可以重复地重复该过程,直到验证结果字符串或者处理超时(502,504,506,510)。
    • 2. 发明申请
    • EXTRACTING USER DATA FROM A SCANNED IMAGE OF A PRE-PRINTED FORM
    • 从预先打印的形式的扫描图像中提取用户数据
    • WO0060531A3
    • 2001-04-05
    • PCT/US0009199
    • 2000-04-07
    • RAF TECHNOLOGY INCELMENHURST BRIAN JTYLER RICHARD H
    • ELMENHURST BRIAN JTYLER RICHARD H
    • G06K9/34G06K9/20
    • G06K9/346G06K2209/01
    • Human and machine readability of pre-printed forms that have been completed with user data is impeded where the user data overlaps zone descriptions, constraint boxes or other markings of the pre-printed form. A "form fracturing" methodology is described that includes processing the composite-image data so as to attach one or more shared pixels to a non-diagonally adjacent data pixel. The remaining form pixels can be removed, resulting in at least a useful approximation and often a complete recovery of the user data. Where blank-form data is not available, a "virtual dropout" technique allows for recovering user data from a pre-printed form using limited speckle size and configurations, constraining gray-scale value, or a combination of the two. The disclosed methodologies are conveniently implemented in software on any digital processor.
    • 在用户数据与预先打印的表格的区域描述,约束框或其他标记重叠的地方,用户数据完成的预打印表单的人机和机器可读性受到阻碍。 描述了“形式压裂”方法,其包括处理复合图像数据以将一个或多个共享像素附着到非对角线相邻的数据像素。 可以去除剩余的形状像素,导致至少有用的近似值,并且经常完全恢复用户数据。 在空格形式数据不可用的情况下,“虚拟删除”技术允许使用有限的散斑大小和配置,约束灰度值或两者的组合从预打印形式恢复用户数据。 所公开的方法在任何数字处理器上以软件方便地实现。
    • 7. 发明申请
    • ADDRESS DISAMBIGUATION FOR MAIL-PIECE ROUTING
    • 用于邮件路由的地址分配
    • WO2003106057A2
    • 2003-12-24
    • PCT/US2003/019336
    • 2003-06-17
    • RAF TECHNOLOGY, INC.ROSS, David, JustinTEUDT, Richard, C.
    • ROSS, David, JustinTEUDT, Richard, C.
    • B07C
    • B07C3/14
    • Improvements are disclosed for automatically routing items, such as mail-piece items (Fig. 2), in support of efficiently and correctly delivering them to an intended destination. A destination address is read by a recognizer (12) but it may be too ambiguous (14,18) initially for routing the piece. The addressee name is also read (24), and the recognizer data is provided to a directory (26) that accesses a name + address database (28). The addressee name is used to disambiguate the recognizer address data (26,30) and thereby properly route the piece (32). In addition, the name + address directory (42,44) can detect incorrect address data (42,50), and notwithstanding the incorrect address, correctly routing the item (52,46) to the intended addressee based on the recognized addressee name (40).
    • 公开了用于自动路由项目(例如邮件项目(图2))的改进,以支持有效且正确地将它们传送到预定目的地。 目的地址由识别器(12)读取,但是对于路由该片段起初可能太模糊(14,18)。 收件人名称也被读取(24),识别器数据被提供给访问名称+地址数据库(28)的目录(26)。 收件人名称用于消除识别器地址数据(26,30)的歧义,从而适当地路由片段(32)。 另外,名称+地址目录(42,44)可以检测到不正确的地址数据(42,50),并且尽管地址不正确,基于所识别的收件人名称(52,46)正确路由到预期的收件人 40)。
    • 8. 发明申请
    • WEIGH ON THE FLY
    • 在飞行上重量
    • WO2009036251A1
    • 2009-03-19
    • PCT/US2008/076140
    • 2008-09-12
    • RAF TECHNOLOGY, INC.TURNER, Bryan, J.
    • TURNER, Bryan, J.
    • G01G19/00G01G19/03G01G19/414
    • G01G19/005G01G19/035G01G19/4148
    • Methods and apparatus for weighing an article, such as a mail piece, while the article is moving, for example along a transport path. In one embodiment, a weigh station comprises a servo motor (110) driven by a servo feed back loop (126, 128) to maintain a selected speed setting (130). When an article is introduced, an impulse is applied to the article sufficient to change its state of motion from its initial state to the selected speed setting. That impulse is applied by the servo motor (110), and the system captures data indicative of the applied impulse, by monitoring the motor current (140, 142). A processor (140) or software converts the captured data to determine a weight of the article, based on stored calibration data (148).
    • 例如沿着传送路径,在物品移动的同时称量诸如邮件的物品的方法和装置。 在一个实施例中,称重站包括由伺服反馈回路(126,128)驱动的伺服电动机(110),以维持所选择的速度设定(130)。 当引入物品时,对物品施加足以将其运动状态从其初始状态改变到所选择的速度设置的脉冲。 该脉冲由伺服电机(110)施加,并且系统通过监视电动机电流(140,142)来捕获表示所施加脉冲的数据。 处理器(140)或软件基于存储的校准数据(148)转换所捕获的数据以确定物品的重量。
    • 10. 发明申请
    • VERIFICATION ENGINE FOR USER AUTHENTICATION
    • 验证发动机用于认证
    • WO0241114A3
    • 2002-09-12
    • PCT/US0146135
    • 2001-10-30
    • RAF TECHNOLOGY INCROSS DAVID JUSTIN
    • ROSS DAVID JUSTIN
    • G06F11/30G06F12/14G06F21/00H04L9/00H04L9/32
    • G06F21/33G06F2221/2103G06Q10/063112G06Q20/0855G06Q20/367G06Q20/3674
    • The verification engine (100) includes various components which include a client interface (102), a database interface (104), and the verification core (106). A subject (108) that either gives or requires authentication communicates with an authentication client (110). The subject (108) can provide identifying information to the authentication client (110), and the subject (108) can also answer queries posed by the authentication client (110). The authentication client (110) gives and receives information to and from the verification core (106) through the client interface (102). The verification core can then provide the information identifying the subject (108) to one or more independent, third-party databases (112a-112d) for authentication database "n" (112d) illustrates that a potentially unlimited number of independent database can be provided for authentication with the verification engine (100). After the subject (108) has identified himself to the authentication client (110), the authentication client (11) can present a predefined query (114) to the subject (108). The actual question and scope of the query depend on the authentication services being provided by the authentication client (11). The subject (108) then returns a response to the query (116). The authentication client (110) then forwards (118) verification engine (100) then transmits (120a-120d) the response from the subject (108) to multiple databases (112a-112d). Each database (112a-112d) that receives the information checks it against the identifying information it stores for the subject (108) and returns a confidence indication (112a-112d) to the verification engine (100). The verification engine (100) combines the individual confidence indications (112a-112d) into a combined confidence indication (124) that is provided to the authentication client (110) for authenticating the subject (108).
    • 验证引擎(100)包括包括客户端接口(102),数据库接口(104)和验证核心(106)的各种组件。 给予或需要认证的主体(108)与认证客户端(110)通信。 对象(108)可以向认证客户机(110)提供识别信息,并且被摄体(108)还可以回答由认证客户机(110)提出的查询。 认证客户端(110)通过客户端接口(102)向验证核心(106)发送信息并从验证核心(106)接收信息。 验证核心然后可以向认证数据库“n”(112d)的一个或多个独立的第三方数据库(112a-112d)提供标识主题(108)的信息(112d),其示出可以提供可能无限数量的独立数据库 用于与验证引擎(100)进行认证。 在对象(108)已经向身份验证客户端(110)识别自己之后,认证客户端(11)可以向对象(108)呈现预定义查询(114)。 查询的实际问题和范围取决于认证客户端(11)提供的认证服务。 主题(108)然后返回对查询(116)的响应。 认证客户端(110)然后转发(118)验证引擎(100)然后将来自对象(108)的响应(120a-120d)发送到多个数据库(112a-112d)。 接收信息的每个数据库(112a-112d)针对对象(108)存储的识别信息进行检查,并向验证引擎(100)返回置信指示(112a-112d)。 验证引擎(100)将个体置信指示(112a-112d)组合成提供给认证客户端(110)以用于认证对象(108)的组合置信指示(124)。