中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.015 seconds)

    METHOD AND SYSTEM FOR MULTI-SCALE CELL IMAGE SEGMENTATION USING MULTIPLE PARALLEL CONVOLUTIONAL NEURAL NETWORKS
    2.
    发明申请
    METHOD AND SYSTEM FOR MULTI-SCALE CELL IMAGE SEGMENTATION USING MULTIPLE PARALLEL CONVOLUTIONAL NEURAL NETWORKS 审中-公开
    利用多个并行卷积神经网络进行多尺度细胞图像分割的方法和系统

    公开(公告)号：WO2018052586A1

    公开(公告)日：2018-03-22

    申请号：PCT/US2017/046151

    申请日：2017-08-09

    Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.

    Inventor： ZHU, Jingwen ,  ZHANG, Yongmian

    IPC: G06N3/02

    CPC classification number: G06K9/6256 ,  G06K9/4628 ,  G06K9/6268 ,  G06K9/6274 ,  G06K9/6292 ,  G06N3/0454 ,  G06T3/4046

    Abstract: An artificial neural network system for image classification, formed of multiple independent individual convolutional neural networks (CNNs), each CNN being configured to process an input image patch to calculate a classification for the center pixel of the patch. The multiple CNNs have different receptive field of views for processing image patches of different sizes centered at the same pixel. A final classification for the center pixel is calculated by combining the classification results from the multiple CNNs. An image patch generator is provided to generate the multiple input image patches of different sizes by cropping them from the original input image. The multiple CNNs have similar configurations, and when training the artificial neural network system, one CNN is trained first, and the learned parameters are transferred to another CNN as initial parameters and the other CNN is further trained. The classification includes three classes, namely background, foreground, and edge.

    Abstract translation: 用于图像分类的人工神经网络系统由多个独立的单独卷积神经网络（CNN）形成，每个CNN被配置为处理输入图像块以计算该块的中心像素的分类 。 多个CNN具有不同的接受视野，用于处理以相同像素为中心的不同大小的图像块。 通过组合来自多个CNN的分类结果来计算中心像素的最终分类。 提供图像补丁生成器以通过从原始输入图像中裁剪出不同大小的多个输入图像补丁。 多个CNN具有相似的配置，并且在训练人工神经网络系统时，首先训练一个CNN，并且将所学习的参数作为初始参数转移到另一个CNN，并且另一个CNN被进一步训练。 分类包括三个类别，即背景，前景和边缘。

    MOTION ESTIMATION THROUGH MACHINE LEARNING
    3.
    发明申请
    MOTION ESTIMATION THROUGH MACHINE LEARNING 审中-公开
    运动估计通过机器学习

    公开(公告)号：WO2017178806A1

    公开(公告)日：2017-10-19

    申请号：PCT/GB2017/051006

    申请日：2017-04-11

    Applicant: MAGIC PONY TECHNOLOGY LIMITED

    Inventor： VAN LEUVEN, Sebastiaan ,  CABALLERO, Jose ,  WANG, Zehan ,  BISHOP, Rob

    IPC: H04N19/53

    CPC classification number: H04N19/53 ,  G06T3/4046 ,  H04N19/159 ,  H04N19/513

    Abstract: The present invention relates to the use of machine learning to improve motion estimation in video encoding. According to a first aspect, there is provided a method for estimating the motion between pictures of video data using a hierarchical algorithm, the method comprising steps of: receiving one or more input pictures of video data; identifying, using a hierarchical algorithm, one or more reference elements in one or more reference pictures of video data that are similar to one or more input elements in the one or more input pictures of video data; determining an estimated motion vector relating the identified one or more reference elements to the one or more input elements; and outputting an estimated motion vector.

    Abstract translation: 本发明涉及使用机器学习来改进视频编码中的运动估计。 根据第一方面，提供了一种使用分层算法来估计视频数据的图片之间的运动的方法，所述方法包括以下步骤：接收视频数据的一个或多个输入图片; 使用分层算法来识别视频数据的一个或一个以上参考图片中的一个或一个以上参考元素，所述参考图片与视频数据的所述一个或一个以上输入图片中的一个或一个以上输入元素类似; 确定将所识别的一个或多个参考元素与所述一个或多个输入元素相关的估计运动向量; 并输出估计的运动矢量。

    FRAME-RECURRENT VIDEO SUPER-RESOLUTION
    5.
    发明申请
    FRAME-RECURRENT VIDEO SUPER-RESOLUTION 审中-公开

    公开(公告)号：WO2019136077A1

    公开(公告)日：2019-07-11

    申请号：PCT/US2019/012064

    申请日：2019-01-02

    Applicant: GOOGLE LLC

    Inventor： VEMULAPALLI, Raviteja ,  BROWN, Matthew Alun ,  SAJJADI, Seyed Mohammad Mehdi

    IPC: G06T3/40

    CPC classification number: G06T3/4053 ,  G06N20/00 ,  G06T3/0093 ,  G06T3/4046 ,  G06T5/50 ,  G06T7/248 ,  G06T2207/20081

    Abstract: The present disclosure provides systems and methods to increase resolution of imagery. In one example embodiment, a computer-implemented method includes obtaining a current low-resolution image frame. The method includes obtaining a previous estimated high-resolution image frame, the previous estimated high-resolution frame being a high-resolution estimate of a previous low-resolution image frame. The method includes warping the previous estimated high-resolution image frame based on the current low-resolution image frame. The method includes inputting the warped previous estimated high-resolution image frame and the current low-resolution image frame into a machine-learned frame estimation model. The method includes receiving a current estimated high-resolution image frame as an output of the machine-learned frame estimation model, the current estimated high-resolution image frame being a high-resolution estimate of the current low-resolution image frame.

    HIERARCHICAL INTERLINKED MULTI-SCALE CONVOLUTIONAL NETWORK FOR IMAGE PARSING
    6.
    发明申请
    HIERARCHICAL INTERLINKED MULTI-SCALE CONVOLUTIONAL NETWORK FOR IMAGE PARSING 审中-公开
    用于图像分割的分层交互式多尺度转换网络

    公开(公告)号：WO2016054802A1

    公开(公告)日：2016-04-14

    申请号：PCT/CN2014/088285

    申请日：2014-10-10

    Applicant: BEIJING KUANGSHI TECHNOLOGY CO., LTD.

    Inventor： YIN, Qi ,  CAO, Zhimin ,  ZHOU, Yisu

    IPC: G06K9/62

    CPC classification number: G06K9/46 ,  G06K9/00228 ,  G06K9/00248 ,  G06K9/4628 ,  G06K9/627 ,  G06K9/66 ,  G06K2009/4666 ,  G06T3/00 ,  G06T3/4046 ,  G06T7/11 ,  G06T11/60

    Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

    Abstract translation: 公开的面部识别系统（和方法）包括面部解析。 在一种方法中，面部解析基于分层互连多尺度卷积神经网络（HIM），以识别面部图像的部件的位置和/或足迹。 HIM从面部图像的不同分辨率图像生成多个级别的图像补丁，其中不同级别的图像补丁具有不同的分辨率。 此外，HIM集成了不同级别的图像补丁，以生成不同级别的互连图像补丁，其中不同级别的互连图像补丁具有不同的分辨率。 此外，HIM组合了互连的图像补丁以识别组件的精细位置和/或足迹。

    REDUCING IMAGE RESOLUTION IN DEEP CONVOLUTIONAL NETWORKS
    9.
    发明申请
    REDUCING IMAGE RESOLUTION IN DEEP CONVOLUTIONAL NETWORKS 审中-公开
    降低深层网络中的图像分辨率

    公开(公告)号：WO2016176095A1

    公开(公告)日：2016-11-03

    申请号：PCT/US2016/028493

    申请日：2016-04-20

    Applicant: QUALCOMM INCORPORATED

    Inventor： ANNAPUREDDY, Venkata Sreekanta Reddy

    IPC: G06N3/08 ,  G06K9/80

    CPC classification number: G06T3/4046 ,  G06K9/4623 ,  G06K9/627 ,  G06K9/66 ,  G06N3/082

    Abstract: A method of reducing image resolution in a deep convolutional network (DCN) includes dynamically selecting a reduction factor to be applied to an input image. The reduction factor can be selected at each layer of the DCN. The method also includes adjusting the DCN based on the reduction factor selected for each layer.

    Abstract translation: 降低深卷积网络（DCN）中的图像分辨率的方法包括动态地选择要应用于输入图像的缩小因子。 可以在DCN的每一层选择还原因子。 该方法还包括基于为每个层选择的减少因子来调整DCN。

Patent Agency Ranking