知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

36 records (took 0.018 seconds)

    Technologies for improved object detection accuracy with multi-scale representation and training
    31.
    发明授权
    Technologies for improved object detection accuracy with multi-scale representation and training 有权

    公开(公告)号：US10262237B2

    公开(公告)日：2019-04-16

    申请号：US15372953

    申请日：2016-12-08

    Applicant: Intel Corporation

    Inventor： Byungseok Roh ,  Kye-Hyeon Kim ,  Sanghoon Hong ,  Minje Park ,  Yeongjae Cheon

    IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04

    Abstract: Technologies for multi-scale object detection include a computing device including a multi-layer convolution network and a multi-scale region proposal network (RPN). The multi-layer convolution network generates a convolution map based on an input image. The multi-scale RPN includes multiple RPN layers, each with a different receptive field size. Each RPN layer generates region proposals based on the convolution map. The computing device may include a multi-scale object classifier that includes multiple region of interest (ROI) pooling layers and multiple associated fully connected (FC) layers. Each ROI pooling layer has a different output size, and each FC layer may be trained for an object scale based on the output size of the associated ROI pooling layer. Each ROI pooling layer may generate pooled ROIs based on the region proposals and each FC layer may generate object classification vectors based on the pooled ROIs. Other embodiments are described and claimed.

    DECOY-BASED MATCHING SYSTEM FOR FACIAL RECOGNITION
    35.
    发明申请
    DECOY-BASED MATCHING SYSTEM FOR FACIAL RECOGNITION 有权

    公开(公告)号：US20170213074A1

    公开(公告)日：2017-07-27

    申请号：US15008186

    申请日：2016-01-27

    Applicant: INTEL CORPORATION

    Inventor： Hyungsoo Lee ,  Yeongjae Cheon ,  Sumin Lee ,  Minje Park

    IPC: G06K9/00 ,  G06F17/30 ,  G06K9/62

    CPC classification number: G06K9/00288 ,  G06F17/30256 ,  G06K9/00281 ,  G06K9/6215

    Abstract: Techniques are provided for facial recognition using decoy-based matching of facial image features. An example method may include comparing extracted facial features of an input image, provided for recognition, to facial features of each of one or more images in a gallery of known faces, to select a closest gallery image. The method may also include calculating a first distance between the input image and the selected gallery image. The method may further include comparing the facial features of the input image to facial features of each of one or more images in a set of decoy faces, to select a closest decoy image and calculating a second distance between the input image and the selected decoy image. The method may further include recognizing a match between the input image and the selected gallery image based on a comparison of the first distance and the second distance.

    Method and Device for Processing Digital Image, and Computer-Readable Recording Medium
    36.
    发明申请
    Method and Device for Processing Digital Image, and Computer-Readable Recording Medium 审中-公开
    用于处理数字图像的方法和设备以及计算机可读记录介质

    公开(公告)号：US20160035073A1

    公开(公告)日：2016-02-04

    申请号：US14883932

    申请日：2015-10-15

    Applicant: Intel Corporation

    Inventor： Minje Park

    IPC: G06T5/40 ,  H04N5/235 ,  G06T5/00 ,  G06K9/62 ,  G06T11/60

    CPC classification number: G06T5/40 ,  G06K9/6212 ,  G06T5/002 ,  G06T5/009 ,  G06T5/50 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20212 ,  H04N5/2353

    Abstract: There is provided a method of processing a digital image including: (a) obtaining a plurality of images; (b) converting the plurality of images into histograms; (c) setting one of the plurality of images as a reference image and another of the plurality of images as a comparison target image; (d) adjusting a distribution of the histogram of the reference image to match a distribution of the histogram of the comparison target image to produce an adjusted reference image; (e) comparing a difference between the adjusted reference image and the comparison target image to produce a masking image; (f) applying the masking image to the comparison target image to produce an adjusted comparison target image; and (g) combining the reference image and the adjusted comparison target image to produce a high dynamic range (HDR) image. Accordingly, even if there is a complex motion on a subject, a clear image without an image overlap or a ghost effect may be obtained when producing the HDR image.

    Abstract translation: 提供了一种处理数字图像的方法，包括：（a）获得多个图像; （b）将所述多个图像转换为直方图; （c）将所述多个图像中的一个作为参考图像和所述多个图像中的另一个作为比较对象图像; （d）调整参考图像的直方图的分布以匹配比较对象图像的直方图的分布，以产生经调整的参考图像; （e）比较调整后的参考图像和比较对象图像之间的差异以产生掩蔽图像; （f）将掩蔽图像应用于比较对象图像，生成调整后的比较对象图像; 和（g）组合参考图像和经调整的比较对象图像以产生高动态范围（HDR）图像。 因此，即使在被摄体上存在复杂的运动，也可以在生成HDR图像时获得没有图像重叠的清晰图像或重影效果。

Patent Agency Ranking