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. 发明公开
    • PROCÉDÉ DE RECONNAISSANCE D'ÉCRITURE MANUSCRITE SUR UNE SURFACE PHYSIQUE
    • VERFAHREN ZUR ERKENNUNG EINES HANDSCHRIFTLICHEN TEXTES AUF EINER PHYSISCHENOBERFLÄCHE
    • EP3109797A1
    • 2016-12-28
    • EP16176132.5
    • 2016-06-24
    • Orange
    • LEFEBVRE, Grégoire
    • G06K9/00G06K9/22G06K9/48G06K9/62
    • G06F3/017G06K9/00402G06K9/00416G06K9/00852G06K9/00872G06K9/00879G06K9/224G06K9/48G06K9/6289G06K2209/01
    • L'invention concerne un procédé de reconnaissance d'écriture manuscrite sur une surface physique à partir de signaux tridimensionnels issus de capteurs d'un terminal, le procédé étant tel que les signaux sont obtenus à partir d'au moins 3 types de capteurs différents, et qu'il comporte des étapes d'échantillonnage selon 3 axes et sur une fenêtre temporelle glissante, de signaux inertiels issus des capteurs, de fusion des signaux échantillonnés en un vecteur à 9 dimensions pour chaque période d'échantillonnage, de conversion des signaux fusionnés en une séquence de vecteurs caractéristiques à 9 dimensions, et lorsqu'un signal caractéristique d'un début de saisie a été détecté, de mémorisation de la séquence de vecteurs caractéristiques dans une liste de séquences de vecteurs caractéristiques, les étapes précédentes étant répétées jusqu'à la détection d'un signal caractéristique d'une fin de saisie, le procédé comportant en outre à la détection dudit signal caractéristique d'une fin de saisie une étape de reconnaissance d'un mot à partir de la liste de séquences de vecteurs caractéristiques constituée sur la fenêtre temporelle.
    • 本发明涉及一种用于基于源自终端的传感器的三维信号在物理表面上识别笔迹的方法,其特征在于,基于至少3种不同类型的传感器获得信号, 并且其包括根据3个轴和滑动时间窗口对源自传感器的惯性信号进行采样的步骤,在每个采样周期将采样信号融合成9维向量,将融合信号转换为序列 特征9维向量的特征向量的特征矢量,当已经检测到输入开始的信号特性时,将特征向量的序列存储在特征向量序列的列表中,重复前述步骤,直到检测到 输入端,所述方法还包括在检测到所述输入端的所述信号特性时,识别所述基底上的单词的步骤 在时间窗口上创建的特征向量序列列表。
    • 2. 发明公开
    • VERFAHREN ZUM BETREIBEN EINES BERÜHRUNGSEMPFINDLICHEN BEDIENSYSTEMS UND BERÜHRUNGSEMPFINDLICHES BEDIENSYSTEM
    • 用于操作触摸感应控制系统和触敏控制系统
    • EP3008572A1
    • 2016-04-20
    • EP14715834.9
    • 2014-03-31
    • Audi AG
    • KÜHNE, Marcus
    • G06F3/0488
    • G06F3/0414B60K35/00B60K37/06B60K2350/1024B60K2350/1032B60K2350/1052G06F3/0412G06F3/04817G06F3/04883G06K9/00167G06K9/00852
    • The invention relates to a method for operating a touch-sensitive operating system (10), in particular for a motor vehicle, wherein a pressure applied to a touch-sensitive operating field (12) by means of an object (18) and a touching position at which the operating field (12) is touched by means of the object (18) are detected. If the detected pressure is less than a specified threshold value, the operating system (10) is operated in a first operating mode, in which a symbol (20) is displayed at a position of a display device (16) corresponding to the detected touching position. If the detected pressure is at least as great as the specified threshold value, the operating system (10) is operated in a second operating mode, in which a mark (22) corresponding to a detected change in the touching position is displayed by means of the display device (16). The invention further relates to a touch-sensitive operating system (10).
    • 本发明涉及一种用于在触敏控制面板(12),并在触摸位置上操作的触摸敏感的操作员控制系统(10),特别是用于汽车上的,其中一个压力上的对象(18)施加与 其中,所述控制面板(12)被触摸与所述对象(18)感测到,worin如果感测到的压力低于规定的阈值时,操作者控制系统(10)在第一操作模式操作时,在其中一个符号 (20)在显示装置(16)做了对应于感测到的触摸位置上的位置被显示,并且如果所感测的压力至少一样大的规定的阈值时,操作者控制系统(10)在操作 第二操作模式,其中,一个字符(22)做了对应于触摸位置的感测到的变化是由所述显示装置(16)的装置显示。 进一步,本发明涉及触敏操作员控制系统(10)。
    • 5. 发明授权
    • HOLISTIC-ANALYTICAL RECOGNITION OF HANDWRITTEN TEXT
    • HOLISTIC-分析检测手写文字
    • EP1362322B1
    • 2007-01-03
    • EP02720749.7
    • 2002-01-03
    • Parascript LLC
    • FILATOV, AlexanderKIL, IgorSEREGIN, Arseni
    • G06K9/68G06K9/72G06K9/00
    • G06K9/6292G06K9/00852
    • In a combined holistic and analytic recognition system, the holistic recognition module will recognize an input word or phrase image by matching an input string of character features for the whole word or phrase against a string of prototype features for a plurality of reference words in a lexicon. This will yield a holistic answer list of recognized word or phrase candidates for the input word or phrase along with a confidence value for each answer on the list. At the same time based on each answer in the answer list, the holistic recognition modules will generate a list of character features and segment the character features into sets of each character in an answer. The analytical recognition module uses segmentation hypotheses from the segmented character feature sets to cut the image of the input string of characters into individual character images. A plurality of character images for the various segmentation hypotheses will be recognized to produce an analytical answer list having a plurality of word or phrase answers for the input word or phrase. Each analytic word answer will have a confidence value based on the combined confidence of recognizing each character. The holistic answer list and the analytic answer list will be examined to find the best answer from the two lists as the recognition of the input handwritten text.
    • 9. 发明公开
    • HOLISTIC-ANALYTICAL RECOGNITION OF HANDWRITTEN TEXT
    • HOLISTIC-分析检测手写文字
    • EP1362322A2
    • 2003-11-19
    • EP02720749.7
    • 2002-01-03
    • Parascript LLC
    • FILATOV, AlexanderKIL, IgorSEREGIN, Arseni
    • G06K9/68G06K9/72G06K9/00
    • G06K9/6292G06K9/00852
    • In a combined holistic and analytic recognition system, the holistic recognition module will recognize an input word or phrase image by matching an input string of character features for the whole word or phrase against a string of prototype features for a plurality of reference words in a lexicon. This will yield a holistic answer list of recognized word or phrase candidates for the input word or phrase along with a confidence value for each answer on the list. At the same time based on each answer in the answer list, the holistic recognition modules will generate a list of character features and segment the character features into sets of each character in an answer. The analytical recognition module uses segmentation hypotheses from the segmented character feature sets to cut the image of the input string of characters into individual character images. A plurality of character images for the various segmentation hypotheses will be recognized to produce an analytical answer list having a plurality of word or phrase answers for the input word or phrase. Each analytic word answer will have a confidence value based on the combined confidence of recognizing each character. The holistic answer list and the analytic answer list will be examined to find the best answer from the two lists as the recognition of the input handwritten text.