-
1.发明申请
公开(公告)号：WO2019114901A1
公开(公告)日：2019-06-20
申请号：PCT/DK2018/050350
申请日：2018-12-12
Applicant: UBIQISENSE APS
Inventor： DINESEN, Palle Geltzer , STANKOVIC, Boris , IBSEN, Per Eld , TAVAKOLI, Mohammad , GØTHGEN, Christoffer
IPC: G06K9/00 , G08B13/196 , G06K9/46
CPC classification number: G06K9/00771 , G06K9/00979 , G06K9/4671 , G06K2009/4695 , G08B13/196 , G08B13/19602 , G08B25/08
Abstract: The present invention relates to a method 100 for object detection (140), recognition, classification and tracking using a distributed networked architecture comprising one or more sensor units (20) wherein the image acquisition and the initial feature extraction are performed and a gateway processor (30) for further data processing. The present invention also relates to a vision system (10) for object detection (140) wherein the method may be implemented, to the devices of the vision system (10), and to the algorithms implemented in the vision system (10) for executing the method acts.
-
2.发明申请
公开(公告)号：WO2018185574A1
公开(公告)日：2018-10-11
申请号：PCT/IB2018/051349
申请日：2018-03-02
Applicant: LENDING SOLUTION S.R.L.
Inventor： MAFODDA, Salvatore , RUIZ GARCIA, Manuel Alejandro
CPC classification number: G06K9/00449 , G03B15/05 , G03B2215/0514 , G03B2215/0539 , G03B2215/0567 , G06K9/00456 , G06K9/00912 , G06K9/00979 , G06K9/2018 , G06K9/2027 , G06K9/22 , G07D7/01 , G07D7/12 , G07D7/2008 , G07D7/2016 , G07D7/206 , G07D7/2083
Abstract: The present invention relates to the context of the personal identification procedures, validation of identity documents, etc. In particular, the present invention proposes to offer a process and a semi-automatic and secure apparatus for recognition and validation of personal identities, identity documents or both at once.
-
公开(公告)号：WO2018164630A1
公开(公告)日：2018-09-13
申请号：PCT/SE2018/050217
申请日：2018-03-07
Applicant: FINGERPRINT CARDS AB
Inventor： WEBER, Sebastian , BURNETT, David
CPC classification number: G06F21/32 , G06F21/60 , G06K9/0002 , G06K9/00979
Abstract: The present invention generally relates to methods for enrolling a user of an electronic device and authentication the user of the electronic device. The electronic device comprising a biometry sensor for acquiring sensing signals representative of a biometric feature, and a processor for computing a verification representation based on said sensing signals. The electronic device further includes a secure module isolated from said processor for computing an encrypted representation of said enrolment representation.
-
公开(公告)号：WO2018129131A1
公开(公告)日：2018-07-12
申请号：PCT/US2018/012306
申请日：2018-01-04
Applicant: QUALCOMM INCORPORATED
Inventor： PARK, Edwin Chongwoo , CHAN, Victor
CPC classification number: G06K9/6257 , G06F15/76 , G06K9/00664 , G06K9/00979 , G06K9/22 , G06K9/6254 , G06K9/6256 , G06K9/6265 , G06K9/6267 , G06K2009/4666 , G06N20/00 , H04L67/20
Abstract: Systems and methods may enable a user who may not have any experience in machine learning to effectively train new models for use in object recognition applications of a device. Embodiments can include, for example, analyzing training data comprising a set of images to determine a set of metrics indicative of a suitability of the training data in machine-learning training for object recognition, and providing an indication of the set of metrics to a user. Additionally or alternatively, an intermediate model can be used, after a first portion of the machine-learning training is conducted, to determine the effectiveness of a remaining portion of negative samples (images without the object) in the training data or to find other negative samples outside of the training data. Identifying and utilizing effective negative samples in this manner can improve the effectiveness of the training.
-
5.发明申请
公开(公告)号：WO2018102440A1
公开(公告)日：2018-06-07
申请号：PCT/US2017/063755
申请日：2017-11-29
Applicant: BLINKER, INC.
Inventor： WILBERT, Anthony, Russell , CHUNG, David, Ching-Chien , WACH, Hans, Brandon , RAUKER, Goran, Matko , WHITE, Solomon, John
CPC classification number: G06K9/3258 , G06K9/00979 , G06K9/22 , G06K2009/363 , G06K2209/15 , G06Q30/0283 , G06Q30/06 , G06Q30/0613 , G06Q40/02
Abstract: A system and method is provided for automatically identifying a vehicle and facilitating a transaction related to the vehicle. The system includes a first mobile apparatus with an image sensor that captures an optical image of a vehicle license plate and convert the optical image into an electrical signal, a license plate detector that identifies the vehicle license plate information, and an interface that transmits the vehicle license plate information. The system further includes a remote server that automatically identifies vehicle configuration information based on the vehicle license plate information, automatically transmits the vehicle configuration information to the first mobile device, and automatically provide for access vehicle sales information in response to a posting request from the first mobile apparatus. Moreover, a second mobile apparatus displays the vehicle sales information and automatically initiates the transaction related to the vehicle in response to a user input.
-
Patent Agency Ranking
公开(公告)号：WO2018031421A1
公开(公告)日：2018-02-15
申请号：PCT/US2017/045584
申请日：2017-08-04
Applicant: X DEVELOPMENT LLC
Inventor： RAJKUMAR, Nareshkumar , HINTERSTOISSER, Stefan , BAJRACHARYA, Max
CPC classification number: G06K9/00664 , B25J9/1697 , G06K9/00979 , G06K9/00993 , G06K9/628 , G06T1/0014 , H04W4/025 , H04W4/60 , H04W4/80 , Y10S901/47
Abstract: Methods, apparatus, systems, and computer-readable media are provided for downloading targeted object recognition modules that are selected from a library of candidate targeted object recognition modules based on various signals. In some implementations, an object recognition client may be operated to facilitate object recognition for a robot. It may download targeted object recognition module(s). Each targeted object recognition module may facilitate inference of an object type or pose of an observed object. The targeted object module(s) may be selected from a library of targeted object recognition modules based on various signals, such as a task to be performed by the robot. The object recognition client may obtain vision data capturing at least a portion of an environment in which the robot operates. The object recognition client may determine, based on the vision data and the downloaded object recognition module(s), information about an observed object in the environment.
Abstract translation: 提供了用于下载基于各种信号从候选目标物体识别模块的库中选择的目标物体识别模块的方法，设备，系统和计算机可读介质。 在一些实施方式中，可以操作对象识别客户端以促进机器人的对象识别。 它可以下载目标识别模块。 每个目标物体识别模块可以帮助推断观察物体的物体类型或姿态。 目标对象模块可以基于各种信号从目标对象识别模块的库中选择，诸如机器人要执行的任务。 物体识别客户端可以获得捕获机器人在其中操作的环境的至少一部分的视觉数据。 对象识别客户端可以基于视觉数据和下载的对象识别模块来确定关于在环境中观察到的对象的信息。
-
公开(公告)号：WO2018023212A1
公开(公告)日：2018-02-08
申请号：PCT/CN2016/092464
申请日：2016-07-30
Applicant: 华为技术有限公司
CPC classification number: G06K9/00624 , G06F3/04842 , G06K9/00664 , G06K9/00979 , G06K9/6253 , G06K9/6256 , G06K9/6267 , G06N3/08
Abstract: 公开了一种图像识别方法及终端，该方法包括：终端获取包含目标物的图像文件；所述终端通过所述终端中的神经网络计算装置根据所述终端中的图像识别模型对所述目标物进行识别，以得到所述目标物的物体类别信息；所述终端将所述物体类别信息作为所述目标物的第一标签信息保存至所述图像文件。可见，能够提高终端进行图像识别的效率，并有效保护终端用户的隐私。
-
公开(公告)号：WO2017119694A1
公开(公告)日：2017-07-13
申请号：PCT/KR2017/000043
申请日：2017-01-03
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： KIM, Hakjoo , PARK, Sangho , PARK, Yong-Jun , LEE, Gwiho , JWA, Ho-Dong , CHOI, Wooyoung
CPC classification number: G06K9/00885 , G06F3/03 , G06F3/147 , G06F21/32 , G06F2221/2115 , G06K9/00979 , G09G5/003 , G09G2358/00 , G09G2370/16 , G09G2380/08
Abstract: Disclosed are an electronic device and a method of operating the same. The electronic device may include a touch screen; a communication interface comprising communication circuitry; and a processor functionally connected to the communication circuitry of the communication interface, wherein the processor may be configured to receive execution information usable for authenticating at least one resource of a second external device from a first external device through the communication circuitry of the communication interface, to display a user interface configured to acquire biometric information of a user through the touch screen in response to receiving the execution information, to generate virtual biometric information based on the acquired biometric information, and to transmit the virtual biometric information to the second external device through the communication circuitry of the communication interface wherein the virtual biometric information is usable for authenticating the at least one resource.
Abstract translation: 公开了一种电子设备及其操作方法。 电子设备可以包括触摸屏; 通信接口，包括通信电路; 以及在功能上连接到通信接口的通信电路的处理器，其中处理器可以被配置为通过通信接口的通信电路从第一外部设备接收可用于认证第二外部设备的至少一个资源的执行信息， 响应于接收到所述执行信息，显示被配置为通过所述触摸屏获取用户的生物信息的用户界面，以基于所获取的生物信息生成虚拟生物测定信息，并且通过将虚拟生物测定信息发送到第二外部设备 通信接口的通信电路，其中虚拟生物计量信息可用于认证至少一个资源。
-
公开(公告)号：WO2016208870A1
公开(公告)日：2016-12-29
申请号：PCT/KR2016/004932
申请日：2016-05-11
Applicant: 렉스젠(주)
Inventor： 안순현
CPC classification number: G06K9/325 , G06K9/00979 , G06K9/00993 , G06K9/32 , G06K9/62 , G06K9/72 , G06K2209/15
Abstract: 본 발명은 차량 번호 판독 장치 및 그 방법에 관한 것이다. 본 발명에 따르면, 차량 번호판 영상을 소정 영역이 포함되도록 복수의 영상으로 분할하는 분할부; 및 상기 복수의 분할 영상을 각 영역에 대응하는 복수의 판독 단말로 배포하고, 상기 복수의 판독 단말 각각으로부터 해당되는 영역에 대한 판독 결과를 수신하는 배포관리부를 포함하는 차량 번호 판독 장치를 제공한다. 이에 따르면, 차량 번호판 영상의 분할 영상들을 서로 다른 지역에 위치하는 판독자들에게 배포함으로써, 운전자의 사생활 침해 가능성을 사전에 차단할 수 있으며, 판독자가 차량의 탑승자 영역에 있는 운전자 및 동승자의 영상을 볼 수 없도록 사전 차단할 수 있다.
Abstract translation: 车牌号码读取装置及其方法技术领域本发明涉及车辆牌照读取装置及其方法。 根据本发明的读取车牌号码的装置包括：分割单元，用于将车辆牌照图像划分为多个图像，使得在多个图像中的每一个中包括预定区域; 以及分配管理单元，用于将多个划分的图像分配到对应于每个区域的多个读取终端，并且从多个读取终端中的每一个接收读取相应区域的结果。 因此，本发明可以将分配有车辆牌照的图像分配给位于不同区域的读取器，从而防止违反驾驶员隐私的可能性，并且防止读者看到驾驶员和乘客的图像在 车辆的乘客舱。
-
公开(公告)号：WO2015073154A1
公开(公告)日：2015-05-21
申请号：PCT/US2014/060547
申请日：2014-10-14
Applicant: GOOGLE INC.
Inventor： WANG, Xiaohang , BISSACCO, Alessandro , BERNTSON, Glen , NAZIF, Marria , SCHEINER, Justin , SHIH, Sam , SNYDER, Mark, Leslie , TALAVERA, Daniel
CPC classification number: G06K9/00463 , G06K9/00979 , G06K9/036 , G06K9/18 , G06K9/4647 , G06K2209/01
Abstract: The technology of the present disclosure includes computer-implemented methods, computer program products, and systems to filter images before transmitting to a system for optical character recognition ("OCR"). A user computing device obtains a first image of the card from the digital scan of a physical card and analyzes features of the first image, the analysis being sufficient to determine if the first image is likely to be usable by an OCR algorithm. If the user computing device determines that the first image is likely to be usable, then the first image is transmitted to an OCR system associated with the OCR algorithm. Upon a determination that the first image is unlikely to be usable, a second image of the card from the digital scan of the physical card is analyzed. The optical character recognition system performs an optical character recognition algorithm on the filtered card.
Abstract translation: 本公开的技术包括计算机实现的方法，计算机程序产品和在发送到用于光学字符识别的系统（“OCR”）之前过滤图像的系统。 用户计算设备从物理卡的数字扫描中获取卡的第一图像并分析第一图像的特征，该分析足以确定第一图像是否可能被OCR算法可用。 如果用户计算设备确定第一图像可能是可用的，则将第一图像发送到与OCR算法相关联的OCR系统。 在确定第一图像不可能使用时，分析来自物理卡的数字扫描的卡的第二图像。 光学字符识别系统在滤波卡上执行光学字符识别算法。
-
-
-
-
-
-
-
-
-
Search Results
164
records
(took 0.027 seconds)
