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
    • 2. 发明申请
    • PRECISION CONSTRAINED GAUSSIAN MODEL FOR HANDWRITING RECOGNITION
    • 精确约束高斯模型用于手写识别
    • US20100246941A1
    • 2010-09-30
    • US12409524
    • 2009-03-24
    • Qiang HuoYongqiang Wang
    • Qiang HuoYongqiang Wang
    • G06K9/62G06K9/46G06K9/18
    • G06K9/222G06K9/6278
    • Described is a technology by which handwriting recognition is performed using a precision constrained Gaussian model (PCGM) that requires far less memory than other models such as MQDF. Offline training, such as via maximum likelihood and/or minimum classification error techniques, provides classification data. The classification data includes basis matrices that are shared by classes, along with weighting coefficients and a mean vector corresponding to each class. The base matrices and weights are obtained by expanding a precision matrix for each class. In online recognition, received handwritten input (e.g., an East Asian character) is classified into a class, based upon the per-class mean vector and weighting coefficients, and the basis matrices, by a PCGM recognizer that outputs similarity scores for candidates and a decision rule that selects the most likely class.
    • 描述了使用精度约束高斯模型(PCGM)执行手写识别的技术,其需要比其他模型如MQDF少得多的存储器。 离线训练,例如通过最大似然和/或最小分类错误技术,提供分类数据。 分类数据包括由类共享的基本矩阵,以及加权系数和对应于每个类的平均向量。 通过扩展每个类的精度矩阵来获得基本矩阵和权重。 在在线识别中,接收到的手写输入(例如,东亚字符)根据每类平均矢量和加权系数以及基准矩阵被分类为输出候选者的相似性分数的PCGM识别器和 选择最可能的类的决策规则。
    • 4. 发明申请
    • SEMI-TIED COVARIANCE MODELLING FOR HANDWRITING RECOGNITION
    • 用于手写识别的半自动混合建模
    • US20100239168A1
    • 2010-09-23
    • US12407791
    • 2009-03-20
    • Qiang HuoYongqiang Wang
    • Qiang HuoYongqiang Wang
    • G06K9/18
    • G06K9/6278
    • Described is a technology by which handwriting recognition is performed using a semi-tied covariance modeling (STC) that requires far less memory than other models such as MQDF. Offline training, such as via maximum likelihood and/or minimum classification error techniques, provides classification data. The classification data includes semi-tied transforms that are shared by classes, along with a class-dependent diagonal matrix and a mean vector corresponding to each class. The semi-tied transforms and class-dependent diagonal matrices are obtained by processing a precision matrix for each class. In online recognition, received handwritten input (e.g., an East Asian character) is classified into a class, based upon the class-dependent diagonal matrices and the semi-tied transforms, by a STC recognizer that outputs similarity scores for candidates and a decision rule that selects the most likely class.
    • 描述了使用半绑合协方差建模(STC)执行手写识别的技术,其需要比其他模型如MQDF少得多的存储器。 离线训练,例如通过最大似然和/或最小分类错误技术,提供分类数据。 分类数据包括由类共享的半连接变换,以及类依赖对角矩阵和对应于每个类的平均向量。 通过处理每个类的精度矩阵获得半绑定变换和类依赖对角矩阵。 在在线识别中,通过输出候选人的相似性分数的STC识别器和决策规则,基于类依赖对角矩阵和半连接变换将接收到的手写输入(例如,东亚字符)分类为类 选择最可能的类。
    • 10. 发明申请
    • Aligning Apparatus and Method for Glass Substrate
    • 玻璃基板对准装置和方法
    • US20140131168A1
    • 2014-05-15
    • US13703692
    • 2012-11-15
    • Zhenhua GuoChunhao WuKunhsien LinYongqiang WangWeibing YangYunshao Jiang
    • Zhenhua GuoChunhao WuKunhsien LinYongqiang WangWeibing YangYunshao Jiang
    • C03B35/16
    • C03B35/16C03B35/163C03B2225/02H01L21/67706H01L21/68Y02P40/57
    • The present invention provides an aligning apparatus for glass substrate to properly align the glass substrate during transfer along a conveyor. The aligning apparatus includes a plurality of rollers, at least a pair of directional beams, at least a pair of positioning devices, a piston, and a detecting device. The detecting device is used to detect whether there is an offset of the glass substrate during the transportation, and the piston will be triggered once an offset is found and determined. The piston will move the positioning device such that a portion of the positioning device which extends to the roller will push the offset glass substrate so as to bring the glass substrate back to the correct position. The present invention also discloses a method to conduct the alignment of the glass substrate. By the disclosure of the present invention, the glass substrate transferred on the rollers can be automatically adjusted and aligned once an offset is found.
    • 本发明提供了一种用于玻璃基板的定位装置,用于在沿输送机传送期间使玻璃基板正确对准。 定位装置包括多个辊,至少一对定向梁,至少一对定位装置,活塞和检测装置。 检测装置用于检测运输过程中是否存在玻璃基板的偏移,一旦找到并确定了偏移,就会触发活塞。 活塞将移动定位装置,使得延伸到辊的定位装置的一部分将推动偏移玻璃基板,以使玻璃基板返回到正确的位置。 本发明还公开了一种进行玻璃基板对准的方法。 通过本发明,传送到辊上的玻璃基板一旦发现偏移就可以被自动调节和对准。