利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

96 records (took 0.019 seconds)

    EFFICIENT DECISION TREE TRAVERSALS IN AN ADAPTIVE BOOSTING (ADABOOST) CLASSIFIER
    1.
    发明公开
    EFFICIENT DECISION TREE TRAVERSALS IN AN ADAPTIVE BOOSTING (ADABOOST) CLASSIFIER 审中-公开
    适应性驱动（ADABOOST）分类器中的有效决策树行程

    公开(公告)号：EP3320488A1

    公开(公告)日：2018-05-16

    申请号：EP16821919.4

    申请日：2016-07-06

    Applicant: Texas Instruments Incorporated

    Inventor： JAGANNATHAN, Shyam ,  SWAMI, Pramod, Kumar

    IPC: G06K9/62 ,  G06F15/173

    CPC classification number: G06N5/02 ,  G06F9/3887 ,  G06K9/00973 ,  G06K9/6257

    Abstract: A method for object classification in a decision tree based adaptive boosting (AdaBoost) classifier implemented on a single-instruction multiple-data (SIMD) processor is provided that includes receiving feature vectors extracted from N consecutive window positions in an image in a memory coupled to the SIMD processor and evaluating the N consecutive window positions concurrently by the AdaBoost classifier using the feature vectors and vector instructions of the SIMD processor, in which the AdaBoost classifier concurrently traverses decision trees for the N consecutive window positions until classification is complete for the N consecutive window positions.

    METHOD FOR TRACKING A TARGET ACOUSTIC SOURCE
    3.
    发明公开
    METHOD FOR TRACKING A TARGET ACOUSTIC SOURCE 审中-公开
    跟踪目标声源的方法

    公开(公告)号：EP3227704A1

    公开(公告)日：2017-10-11

    申请号：EP15818045.5

    申请日：2015-11-18

    Applicant: Fondazione Istituto Italiano di Tecnologia

    Inventor： CROCCO, Marco ,  MURINO, Vittorio ,  TRUCCO, Andrea ,  MARTELLI, Samuele

    IPC: G01S3/80 ,  G01S3/801 ,  G01S5/18

    CPC classification number: G01S5/18 ,  G01S3/8006 ,  G01S3/801 ,  G01S7/539 ,  G06K9/0055 ,  G06K9/6257 ,  G06T11/206 ,  G06T11/60 ,  G06T15/08

    Abstract: A method of processing an acoustic image includes the steps of acquiring acoustic signals generated by acoustic sources in a predetermined region of space, generating a multispectral 3D acoustic image that includes a collection of 2D acoustic images, performing a frequency integration of the multispectral acoustic image for generating a 2D acoustic map locating at least one target acoustic source of interest and modeling the signal spectrum associated with the target acoustic source, generating a classification map obtained by comparing the signal spectrum of each signal associated with each pixel of the multispectral acoustic image and the model of the signal spectrum associated with the target acoustic source to distinguish the spectrum of the signal associated with the target acoustic source from the signal spectra associated with the remaining acoustic sources, and merging the classification map and the acoustic map to obtain a merged map.

    Abstract translation: 一种处理声学图像的方法，提供以下步骤：a）获取由空间的预定区域中的声源产生的声学信号，b）产生多光谱3D声学图像（1），其由2D声学图像的集合组成 2D声学图像通过将每个获取的声源的位置转换为灰度或彩色模型而形成，每个2D声学图像由单个频率或频带识别，使得每个2D声学图像具有 沿着2D图像的坐标轴标记在其上的每个检测到的音频源，用于获取的声源的空间分配，c）执行所述多谱声学图像的频率积分以生成2D声学图。 该方法还提供另外的以下步骤：d）定位至少一个感兴趣的目标声源并对与所述目标声源相关联的信号频谱建模，e）生成通过比较与每个信号相关联的每个信号的信号频谱获得的分类图 所述比较是通过训练分类算法获得的，所述分类算法针对所述多光谱声学图像的每个像素执行，从而区分所述多光谱声学图像的像素和与所述目标声学源相关联的信号谱的模型 与来自与剩余声源相关联的信号频谱的目标声源相关联的信号，f）合并所述分类图和所述声学图以获得合并图。

    IMAGE PROCESSING SYSTEM
    4.
    发明公开
    IMAGE PROCESSING SYSTEM 审中-公开
    图像处理系统

    公开(公告)号：EP3213257A1

    公开(公告)日：2017-09-06

    申请号：EP16782208.9

    申请日：2016-10-12

    Applicant: FotoNation Limited

    Inventor： NICOARA, Nicolae ,  RACEALA, Cristina ,  ZAHARIA, Corneliu ,  FULOP, Szabolcs ,  IOVITA, Oana

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

    CPC classification number: G06K9/00228 ,  G06K9/00986 ,  G06K9/6202 ,  G06K9/6257

    Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.

    Abstract translation: 图像处理系统包括模板匹配引擎（TME）。 TME从内存中读取图像; 并且随着图像的每个像素被读取，作为像素值的函数来计算多个特征地图的相应特征值。 预滤波器响应于包括有限检测器级联内的节点的当前像素位置以被应用于图像内的窗口，以：将来自与像素位置对应的多个特征地图中的选定一个的特征值与 阈值; 并且响应于有限检测器级联内的所有节点的像素被应用于已被读取的窗口，确定该窗口的分数。 响应于指示窗口的分数低于窗口阈值的预过滤器，响应于所述前置过滤器的分类器在指示窗口不包括待检测的对象之前不向窗口应用更长的检测器级联。

    METHOD AND SYSTEM FOR FACE IMAGE RECOGNITION
    5.
    发明公开
    METHOD AND SYSTEM FOR FACE IMAGE RECOGNITION 审中-公开
    VERFAHREN UND SYSTEM ZUR GESICHTSBILDERKENNUNG

    公开(公告)号：EP3074918A1

    公开(公告)日：2016-10-05

    申请号：EP13898047.9

    申请日：2013-11-30

    Applicant: Beijing Sensetime Technology Development Co., Ltd.

    Inventor： SUN, Yi ,  WANG, Xiaogang ,  TANG, Xiaoou

    IPC: G06K9/00

    CPC classification number: G06K9/00288 ,  G06K9/00281 ,  G06K9/4604 ,  G06K9/4628 ,  G06K9/4652 ,  G06K9/6257 ,  G06K9/66

    Abstract: A method for face image recognition is disclosed. The method comprises generating one or more face region pairs of face images to be compared and recognized; forming a plurality of feature modes by exchanging the two face regions of each face region pair and horizontally flipping each face region of each face region pair; receiving, by one or more convolutional neural networks, the plurality of feature modes, each of which forms a plurality of input maps in the convolutional neural network; extracting, by the one or more convolutional neural networks, relational features from the input maps, which reflect identity similarities of the face images; and recognizing whether the compared face images belong to the same identity based on the extracted relational features of the face images. In addition, a system for face image recognition is also disclosed.

    Abstract translation: 公开了一种面部图像识别方法。 该方法包括生成要比较和识别的面部图像的一个或多个面部区域对; 通过交换每个面部区域对的两个面部区域并水平地翻转每个面部区域对的每个面部区域来形成多个特征模式; 通过一个或多个卷积神经网络接收多个特征模式，每个特征模式在卷积神经网络中形成多个输入图; 由一个或多个卷积神经网络提取来自输入图的关系特征，其反映面部图像的身份相似性; 并且基于所提取的面部图像的关系特征来识别比较的脸部图像是否属于相同的身份。 此外，还公开了一种用于面部图像识别的系统。

    Information processing device, information processing method, and program
    6.
    发明公开
    Information processing device, information processing method, and program 审中-公开
    Informationsverarbeitungsvorrichtung，Informationsverarbeitungsverfahren und Programm

    公开(公告)号：EP2887261A3

    公开(公告)日：2016-03-09

    申请号：EP14189271.1

    申请日：2014-10-16

    Applicant: Sony Corporation

    Inventor： Yokono, Jun

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06F3/042

    CPC classification number: G06K9/00523 ,  G06F3/042 ,  G06F3/0428 ,  G06F2203/04108 ,  G06K9/00228 ,  G06K9/00382 ,  G06K9/00503 ,  G06K9/4614 ,  G06K9/4619 ,  G06K9/6256 ,  G06K9/6257

    Abstract: An information processing device includes a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit. The feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied.

    Abstract translation: 信息处理装置包括：特征量提取单元，被配置为从通过连接从不同视点拍摄的图像生成的连接图像中提取每个特征量; 以及特定对象识别单元，被配置为基于由特征量提取单元提取的特征量来执行确定特定对象的位置的处理。 特征量提取单元执行特征量提取处理，其中应用了设置分离滤波器形成区域的分离滤波器。

    Face detector training method, face detection method, and apparatus
    9.
    发明公开
    Face detector training method, face detection method, and apparatus 有权
    Gesichtsdetektorschulungsverfahren，Gesichtserkennungsverfahren und Vorrichtung

    公开(公告)号：EP2908268A2

    公开(公告)日：2015-08-19

    申请号：EP15154873.2

    申请日：2015-02-12

    Applicant: Huawei Technologies Co., Ltd.

    Inventor： Zhang, Yu ,  Chai, Zhenhua ,  Du, Zhijun

    IPC: G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/00288 ,  G06K9/00228 ,  G06K9/6257 ,  G06K2009/4666 ,  G06N99/005

    Abstract: Embodiments of the present invention provide a face detector training method, a face detection method, and apparatuses. In the present invention, during a training phase, a flexible block based local binary pattern feature and a corresponding second classifier are constructed, appropriate second classifiers are searched for to generate multiple first classifiers, and multiple layers of first classifiers that are obtained by using a cascading method form a final face detector; and during a detection phase, face detection is performed on a to-be-detected image by using a first classifier or a face detector that is learned during a training process, so that a face is differentiated from a non-face, and a face detection result is combined and output. During this process, each FBLBP feature includes one pivot block and at least one neighbor block. The pivot block and the neighbor block are equal in size, and positions of each neighbor block and the pivot block are not strictly limited. Therefore, flexibility is high, robustness is improved, and meanwhile a false detection rate is reduced.

    Abstract translation: 本发明的实施例提供一种面部检测器训练方法，面部检测方法和装置。 在本发明中，在训练阶段期间，构建基于灵活块的局部二进制模式特征和对应的第二分类器，搜索合适的第二分类器以生成多个第一分类器，以及通过使用 级联方法形成最终的面部检测器; 并且在检测阶段期间，通过使用在训练处理期间学习的第一分类器或面部检测器对被检测图像执行面部检测，使得脸部与非脸部区分开，并且脸部 检测结果合并输出。 在此过程中，每个FBLBP功能包括一个枢轴块和至少一个相邻块。 枢轴块和相邻块的大小相等，并且不严格限制每个相邻块和枢轴块的位置。 因此，灵活性高，鲁棒性提高，同时误检率降低。

    Method and apparatus for generating strong classifier for face detection
    10.
    发明公开
    Method and apparatus for generating strong classifier for face detection 有权
    用于产生用于面部识别的强分类器的方法和装置

    公开(公告)号：EP2879078A3

    公开(公告)日：2015-08-19

    申请号：EP14191684.1

    申请日：2014-11-04

    Applicant: Huawei Technologies Co., Ltd.

    Inventor： Zhang, Yu ,  Du, Zhijun ,  Wang, Minjie

    IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC classification number: G06K9/00295 ,  G06K9/00221 ,  G06K9/4614 ,  G06K9/6256 ,  G06K9/6257 ,  G06K2009/4666

    Abstract: Embodiments of the present invention disclose a method for generating a strong classifier for face detection, and the method includes: determining, according to a size of a prestored image training sample, a parameter of at least one weak classifier of the image training sample; obtaining a sketch value of each of the weak classifiers of the image training sample according to a preset threshold of a weak classifier and the parameter of each of the weak classifiers; calculating a weighted classification error of each of the weak classifiers according to the sketch value and an initial weight of the image training sample, and obtaining at least one optimal weak classifier according to the weighted classification error; and generating a strong classifier for face detection according to the optimal weak classifiers. The embodiments of the present invention further disclose an apparatus for generating a strong classifier for face detection. The embodiments of the present invention have advantages of improving robustness of code against noise and reducing a false detection rate of face detection.

Patent Agency Ranking