-
21.发明授权公开(公告)号：US11222200B2
公开(公告)日：2022-01-11
申请号：US16789507
申请日：2020-02-13
申请人： TENCENT AMERICA LLC
发明人： Shih-Yao Lin , Yusheng Xie , Hui Tang , Chao Huang , Lianyi Han , Wei Fan
摘要： A method, computer program, and computer system is provided for estimating three-dimensional hand poses in images. Data corresponding to two hand images is receive, and an optical flow value corresponding to a change in a hand gesture in the received hand image data is calculate. A heat map is generated based on the calculated optical flow, and a hand mesh map is estimated based on the generated heat map. A hand pose present within the hand images is determined based on the estimated hand mesh map.
-
公开(公告)号：US20210174365A1
公开(公告)日：2021-06-10
申请号：US17181754
申请日：2021-02-22
摘要： A method for improved security at automated teller machines (ATMs) comprising: capturing, by a first camera at an ATM, one or more images of a bank card; reading card information from the bank card by processing the one or more images of the bank card, wherein the card information comprises an account number and an expiration date; receiving, from an input device at the ATM, a personal identification number (PIN) entered by a user; sending a request to a server device to verify the card information and the PIN; and in response receiving a response from the server device, allowing the user to transact with the ATM.
-
公开(公告)号：US10929846B2
公开(公告)日：2021-02-23
申请号：US16361787
申请日：2019-03-22
摘要： A method for improved security at automated teller machines (ATMs) comprising: capturing, by a first camera at an ATM, one or more images of a bank card; reading card information from the bank card by processing the one or more images of the bank card, wherein the card information comprises an account number and an expiration date; receiving, from an input device at the ATM, a personal identification number (PIN) entered by a user; sending a request to a server device to verify the card information and the PIN; and in response receiving a response from the server device, allowing the user to transact with the ATM.
-
公开(公告)号：US20200302755A1
公开(公告)日：2020-09-24
申请号：US16361787
申请日：2019-03-22
摘要： A method for improved security at automated teller machines (ATMs) comprising: capturing, by a first camera at an ATM, one or more images of a bank card; reading card information from the bank card by processing the one or more images of the bank card, wherein the card information comprises an account number and an expiration date; receiving, from an input device at the ATM, a personal identification number (PIN) entered by a user; sending a request to a server device to verify the card information and the PIN; and in response receiving a response from the server device, allowing the user to transact with the ATM.
-
公开(公告)号：US10354472B2
公开(公告)日：2019-07-16
申请号：US15319441
申请日：2015-06-19
申请人： FACEBOOK, INC.
发明人： Theodore Kuklinski , Bruce Monk
摘要： A computerized system for classifying and authenticating documents is provided. The Classification process involves the creation of a Unique Pair Feature Vector which provides the best discrimination information for each pair of Document Classes at every node in a Pairwise Comparison Nodal Network. The Nodal Network has a plurality of nodes, each node corresponding to the best discrimination information between two potential document classes. By performing a pairwise comparison of the potential documents using this nodal network, the document is classified. After classification, the document can be authenticated for validity.
-
公开(公告)号：US20150213330A1
公开(公告)日：2015-07-30
申请号：US14508492
申请日：2014-10-07
发明人： Yuri Chulinin
CPC分类号： G06F17/2863 , G06K9/00973 , G06K9/4647 , G06K9/4685 , G06K2209/01 , G06K2209/25
摘要： The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify a subset of the total number of symbols frequently used in the scanned document image or images. One or more lists of graphemes for the language of the text are then ordered in most-likely-occurring to least-likely-occurring order to facilitate a second optical-character-recognition step in which symbol images extracted from the one or more scanned-document images are associated with one or more graphemes most likely to correspond to the scanned symbol image.
摘要翻译： 本文件涉及用于识别对应于扫描文档图像或其他含文本图像中的符号图像的符号的方法和系统，其中包含与中文或日文字符对应的符号，韩文形式音节块或符号 使用大量符号进行写入和打印的其他语言。 在一个实现中，当前文档所针对的方法和系统在一个或多个扫描图像上执行初始处理步骤，以识别经扫描的文档图像或图像中经常使用的符号总数的子集。 然后以最有可能发生到最不可能发生的顺序排列文本语言的一个或多个字母表格，以促进第二光学字符识别步骤，其中从一个或多个扫描 - 文档图像与最可能对应于被扫描的符号图像的一个或多个图形相关联。
-
27.发明申请Method and Apparatus for Automatic Application and Monitoring of a Structure to be Applied Onto a Substrate 有权用于自动应用和监测应用于基板的结构的方法和装置公开(公告)号：US20080024602A1
公开(公告)日：2008-01-31
申请号：US10584120
申请日：2004-07-16
CPC分类号： G01N21/88 , B05B12/126 , B05C5/0216 , G06K9/32 , G06T7/0004 , Y10T156/10
摘要： A method and apparatus are provided for automatic application and monitoring of a structure to be applied onto substrate. A plurality of cameras positioned around an application facility are utilized to monitor the automatic application of a structure on a substrate by means of a stereometry procedure. Three-dimensional recognition of a reference contour position results in the overlapping area to be used for gross adjustment of the application facility prior to applying the structure.
摘要翻译： 提供了一种方法和装置，用于自动应用和监测要施加到基板上的结构。 利用位于应用设施周围的多个照相机，通过立体成像程序来监视基板上的结构的自动应用。 参考轮廓位置的三维识别导致在施加结构之前用于应用设施的总体调整的重叠区域。
-
公开(公告)号：US20050099410A1
公开(公告)日：2005-05-12
申请号：US10703310
申请日：2003-11-07
IPC分类号： G01B11/30 , G06F3/03 , G06F3/033 , G06K9/52 , G06K9/58 , G06K9/64 , G06K9/82 , G06T7/00 , G09G5/00
CPC分类号： G06F3/0317
摘要： One embodiment in accordance with the invention relates to detecting a homogeneous surface. A first surface image is received. A plurality of values are generated by performing a plurality of auto correlations with the first surface image and a copy of the first surface image. The plurality of values includes a first peak value. A determination is made as to whether a normalized second peak value of the plurality of values satisfies a defined condition associated with a value. If so, a homogeneous surface image filter is utilized with a second surface image.
摘要翻译： 根据本发明的一个实施例涉及检测均匀的表面。 接收第一表面图像。 通过与第一表面图像和第一表面图像的副本执行多个自动相关来生成多个值。 多个值包括第一峰值。 确定多个值的归一化第二峰值是否满足与值相关联的限定条件。 如果是这样，则使用均匀的表面图像滤波器与第二表面图像。
-
公开(公告)号：US4803737A
公开(公告)日：1989-02-07
申请号：US104525
申请日：1987-09-30
申请人： Yoichi Sato , Kazuo Ichinokawa
发明人： Yoichi Sato , Kazuo Ichinokawa
CPC分类号： G06F3/0317 , G06F3/0321
摘要： A novel digitizer operable on an optical digitization basis comprises a transparent flat plate as a light active surface located on a graphic data recording medium, and a cursor functioning as an optical recognition device movable on the transparent flat plate. A predetermined coordinate correlative pattern is described on or in the transparent flat plate with a fluorescent paint. The cursor comprises a positioning arm provided on the outer periphery thereof to visually trace a data location on the recording medium in accordance with a movement of the cursor to effect positioning of the cursor with respect to the data location, an optical system including a light source, an optical filter assembly, and a light focusing lens etc., and a CCD sensor unit to sense light emitted from a partial pattern which falls within a predetermined limited visual range of the pattern. By irradiation of the pattern, fluorescent light is emitted therefrom. The optical digitizer is operative to determine position coordinates of a graphic data on the recording medium in accordance with an projected image of fluorescent light sensed by the sensor unit. Thus, such an implementation makes it possible to realize a small-sized, high accuracy digitizer completely free from influence of electromagnetic wave noise.
摘要翻译： 基于光学数字化操作的新型数字转换器包括作为位于图形数据记录介质上的光活性表面的透明平板和用作在透明平板上可移动的光学识别装置的光标。 在具有荧光涂料的透明平板上或其中描述预定的坐标相关图案。 光标包括设置在其外周上的定位臂，以根据光标的移动来视觉地跟踪记录介质上的数据位置，以实现光标相对于数据位置的定位;光学系统，包括光源 ，光学滤光器组件和光聚焦透镜等，以及CCD传感器单元，用于感测从部分图案发射的光，其落入图案的预定的有限视觉范围内。 通过照射图案，从其发射荧光。 光学数字转换器用于根据由传感器单元感测的荧光的投影图像来确定记录介质上的图形数据的位置坐标。 因此，这样的实现使得可以实现完全不受电磁波噪声影响的小型，高精度数字化仪。
-
公开(公告)号：US4735487A
公开(公告)日：1988-04-05
申请号：US797349
申请日：1985-11-12
申请人： Gunter Thorwirth , Detlef Biernat , Gerhard Kuehn
发明人： Gunter Thorwirth , Detlef Biernat , Gerhard Kuehn
摘要： An apparatus for analyzing two-dimensional input objects comprising an illumination system including a lighting unit, a Fourier transform module and a receiver unit. The lighting unit generates an incoherent illuminating beam of predetermined form and area, for what purpose the lighting unit may include a self-luminous mask or an incoherently illuminated mask. A receiver unit comprises a single detector which is arranged in the optical axis of the Fourier transform plane of the Fourier transform module. The exit of the lighting unit is located on the optical axis and is imaged by the subsequent imaging optical elements (inclusive of the Fourier transform module) at the Fourier transform plane of the Fourier transform module.
摘要翻译： 一种用于分析二维输入物体的装置，包括包括照明单元，傅里叶变换模块和接收器单元的照明系统。 照明单元产生预定形式和面积的非相干照明光束，为什么照明单元可以包括自发光掩模或不相干照明的掩模。 接收机单元包括布置在傅里叶变换模块的傅立叶变换平面的光轴上的单个检测器。 照明单元的出口位于光轴上，并且通过傅立叶变换模块的傅立叶变换平面处的随后的成像光学元件（包括傅立叶变换模块）成像。
-
-
-
-
-
-
-
-
-
搜索结果
66 条记录 (耗时 0.017 秒)
