利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

338 条记录 (耗时 0.022 秒)

    METHOD AND DEVICE FOR AUTHENTICATING IDENTIFY BY MEANS OF FUSION OF MULTIPLE BIOLOGICAL CHARACTERISTICS
    4.
    发明申请
    METHOD AND DEVICE FOR AUTHENTICATING IDENTIFY BY MEANS OF FUSION OF MULTIPLE BIOLOGICAL CHARACTERISTICS 审中-公开

    公开(公告)号：US20180285542A1

    公开(公告)日：2018-10-04

    申请号：US15765253

    申请日：2016-03-29

    申请人： GRG BANKING EQUIPMENT CO., LTD.

    发明人： Zheng XIAO ,  Jiachun ZHENG ,  Xiaoping HAN ,  Jinjun HE

    IPC分类号： G06F21/32 ,  G06N7/00

    CPC分类号： G06F21/32 ,  G06K9/00892 ,  G06K9/629 ,  G06N7/005 ,  H04L63/0861

    摘要： Provided are a method and device for authenticating an identity based on fusion of multiple biological characteristics. The method includes: collecting at least two types of biological characteristic identity information of a to-be-identified user; performing characteristic extraction on each type of the collected biological characteristic identify information, to obtain characteristic information corresponding to the type; establishing characteristic matrixes based on the characteristic information; performing normalization processing on each of the characteristic matrixes; performing dynamic weighting fusion on all of the normalized characteristic matrixes, to obtain a fused characteristic matrix; matching the fused characteristic matrix with a preset standard matrix, to obtain a matching score; and obtaining an identity identification result of the to-be-identified user based on a Bayesian decision model and the matching score.

    BIOMETRIC METHOD
    7.
    发明申请
    BIOMETRIC METHOD 审中-公开

    公开(公告)号：US20180144184A1

    公开(公告)日：2018-05-24

    申请号：US15786706

    申请日：2017-10-18

    申请人： BioID AG

    发明人： Robert Frischholz ,  Hagen Zurek

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00288 ,  G06K9/00228 ,  G06K9/00281 ,  G06K9/00597 ,  G06K9/6202 ,  G06K9/6255 ,  G06K9/629

    摘要： The method according to the invention is based on a first image of a first eye region of a person and a second image of a second eye region of the person, wherein the first eye region contains one of the eyes of the person, for example the right eye, and the second eye region contains the other eye of the person, for example the left eye; one of the images is mirrored, and the mirrored and the non-mirrored image are combined in the position space and/or in the feature space, in order to generate a template of an overlaid image. The template contains biometric features for person recognition.

    SYSTEMS AND METHODS FOR DETECTING MOTION BASED ON A VIDEO PATTERN
    8.
    发明申请
    SYSTEMS AND METHODS FOR DETECTING MOTION BASED ON A VIDEO PATTERN 审中-公开

    公开(公告)号：US20180033271A1

    公开(公告)日：2018-02-01

    申请号：US15220996

    申请日：2016-07-27

    申请人： Honeywell International Inc.

    发明人： Xiaomin Xia ,  Di Wu ,  Chao Liu ,  Tianfeng Zhao

    IPC分类号： G08B13/196 ,  G02B3/08 ,  G02B13/14

    CPC分类号： G08B13/19602 ,  G02B3/08 ,  G02B13/14 ,  G06K9/00771 ,  G06K9/629 ,  G06K9/6293

    摘要： Some systems and methods for detecting motion based on a video pattern can include creating a motion image from a sequence of raw images, masking the motion image with a lens pattern associated with a PIR sensor and an associated Fresnel lens, splitting each of a plurality of blocks of the lens pattern into first and second negative areas, identifying a positive area pixel value as a sum of all pixels in the motion image aligned with the first positive area in the plurality of blocks, identifying a negative area pixel value as a sum of all pixels in the motion image aligned with the second negative area in the plurality of blocks, identifying a motion image response value as a difference between the positive and negative area pixel values, and identifying a presence of motion when the motion image response value exceeds a predetermined value.

    SKELETON -BASED ACTION DETECTION USING RECURRENT NEURAL NETWORK
    9.
    发明申请
    SKELETON -BASED ACTION DETECTION USING RECURRENT NEURAL NETWORK 有权

    公开(公告)号：US20170344829A1

    公开(公告)日：2017-11-30

    申请号：US15169593

    申请日：2016-05-31

    申请人： Microsoft Technology Licensing, LLC

    发明人： Cuiling Lan ,  Wenjun Zeng ,  Wentao Zhu ,  Junliang Xing

    IPC分类号： G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

    CPC分类号： G06K9/00718 ,  G06K9/00369 ,  G06K9/4628 ,  G06K9/629 ,  G06K2009/00738 ,  G06N3/0445 ,  G06N3/08 ,  G06T7/0042 ,  G06T7/33 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084

    摘要： In implementations of the subject matter described herein, an action detection scheme using a recurrent neural network (RNN) is proposed. Joint locations for a skeleton representation of an observed entity in a frame of a video and a predefined action label for the frame are obtained to train a learning network including RNN elements and a classification element. Specifically, first weights for mapping the joint locations to a first feature for the frame generated by a first RNN element in a learning network and second weights for mapping the joint locations to a second feature for the frame generated by a second RNN element in the learning network are determined based on the joint locations and the predefined action label. The first and second weights are determined by increasing a first correlation between the first feature and a first subset of the joint locations and a second correlation between the second feature and the first subset of the joint locations. Based on the joint locations and the predefined action label, a parameter for a classification element included in the learning network is also determined by increasing a probability of the frame being associated with the predefined action label. The probability is generated by the classification element at least based on the first and second features.

    Image matching method using feature point matching
    10.
    发明授权
    Image matching method using feature point matching 有权

    公开(公告)号：US09824303B2

    公开(公告)日：2017-11-21

    申请号：US14529875

    申请日：2014-10-31

    申请人： HANWHA TECHWIN CO., LTD.

    发明人： Jaeyoon Oh

    IPC分类号： G06K9/62

    CPC分类号： G06K9/629 ,  G06K9/6211

    摘要： An image matching method includes: extracting a plurality of feature points from a reference image; selecting a first feature point from the feature points, and selecting a first reference search area comprising the first feature point; setting a first matching candidate search area corresponding to the first reference search area from a target image, and extracting a plurality of feature points from the first matching candidate search area; selecting a second feature point closest to the first feature point in the first reference search area, and selecting a first straight line connecting the first and second feature points; generating a plurality of segments from the feature points extracted from the first matching candidate search area; and determining a first matching straight line matching a length and an angle of the first straight line, from the segments generated from the feature points extracted from the first matching candidate search area.