中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

125 records (took 0.028 seconds)

    METHOD AND APPARATUS FOR FACE RECOGNITION
    13.
    发明申请
    METHOD AND APPARATUS FOR FACE RECOGNITION 审中-公开
    用于脸部识别的方法和装置

    公开(公告)号：US20170046563A1

    公开(公告)日：2017-02-16

    申请号：US15189454

    申请日：2016-06-22

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Jungbae KIM ,  Ruslan SALAKHUTDINOV ,  Jaejoon HAN ,  Byungin YOO

    IPC: G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/00275 ,  G06K9/00241 ,  G06K9/00288 ,  G06K9/4628 ,  G06K9/4661 ,  G06K9/6262 ,  G06K9/6272

    Abstract: A training method of training an illumination compensation model includes extracting, from a training image, an albedo image of a face area, a surface normal image of the face area, and an illumination feature, the extracting being based on an illumination compensation model; generating an illumination restoration image based on the albedo image, the surface normal image, and the illumination feature; and training the illumination compensation model based on the training image and the illumination restoration image.

    Abstract translation: 训练照明补偿模式的训练方法包括从训练图像中提取面部区域的反照率图像，面部区域的表面法线图像和照明特征，所述提取基于照明补偿模型; 基于反照率图像，表面法线图像和照明特征生成照明恢复图像; 并基于训练图像和照明恢复图像训练照明补偿模型。

    FACE RECOGNITION METHOD AND APPARATUS
    14.
    发明申请
    FACE RECOGNITION METHOD AND APPARATUS 审中-公开
    脸部识别方法和装置

    公开(公告)号：US20160379041A1

    公开(公告)日：2016-12-29

    申请号：US15188437

    申请日：2016-06-21

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Seon Min RHEE ,  Jungbae KIM ,  Byungin YOO ,  Jaejoon HAN ,  Seungju HAN

    IPC: G06K9/00 ,  G06K9/62 ,  G06T15/20

    CPC classification number: G06K9/00275 ,  G06K9/00208 ,  G06K9/00248 ,  G06K9/00288 ,  G06K9/6271 ,  G06K9/6296 ,  G06T15/04 ,  G06T19/20 ,  G06T2219/2021

    Abstract: Face recognition of a face, to determine whether the face correlates with an enrolled face, may include generating a personalized three-dimensional (3D) face model based on a two-dimensional (2D) input image of the face, acquiring 3D shape information and a normalized 2D input image of the face based on the personalized 3D face model, generating feature information based on the 3D shape information and pixel color values of the normalized 2D input image, and comparing the feature information with feature information associated with the enrolled face. The feature information may include first and second feature information generated based on applying first and second deep neural network models to the pixel color values of the normalized 2D input image and the 3D shape information, respectively. The personalized 3D face model may be generated based on transforming a generic 3D face model based on landmarks detected in the 2D input image.

    Abstract translation: 面部识别，以确定面部与登记面部相关是否可以包括基于面部的二维（2D）输入图像生成个性化三维（3D）面部模型，获取3D形状信息和 基于个性化3D脸部模型的面部的归一化2D输入图像，基于3D形状信息和归一化2D输入图像的像素颜色值生成特征信息，以及将特征信息与与注册面相关联的特征信息进行比较。 特征信息可以包括基于将第一和第二深层神经网络模型应用于归一化2D输入图像和3D形状信息的像素颜色值而生成的第一和第二特征信息。 可以基于基于在2D输入图像中检测到的地标来变换通用3D脸部模型来生成个性化3D脸部模型。

    METHOD AND APPARATUS FOR GENERATING PERSONALIZED 3D FACE MODEL
    16.
    发明申请
    METHOD AND APPARATUS FOR GENERATING PERSONALIZED 3D FACE MODEL 有权
    用于生成个性化3D面部模型的方法和装置

    公开(公告)号：US20160148425A1

    公开(公告)日：2016-05-26

    申请号：US14882624

    申请日：2015-10-14

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Youngkyoo HWANG ,  Jungbae KIM ,  Seon Min RHEE ,  Jaejoon HAN

    IPC: G06T17/20 ,  G06T15/04 ,  G06K9/00

    CPC classification number: G06T17/20 ,  G06K9/00208 ,  G06K9/00268 ,  G06K9/00281 ,  G06T15/04 ,  G06T17/00

    Abstract: A method of generating a three-dimensional (3D) face model includes extracting feature points of a face from input images comprising a first face image and a second face image; deforming a generic 3D face model to a personalized 3D face model based on the feature points; projecting the personalized 3D face model to each of the first face image and the second face image; and refining the personalized 3D face model based on a difference in texture patterns between the first face image to which the personalized 3D face model is projected and the second face image to which the personalized 3D face model is projected.

    Abstract translation: 一种生成三维（3D）面部模型的方法包括从包括第一面部图像和第二面部图像的输入图像中提取面部的特征点; 基于特征点将通用3D人脸模型变形为个性化3D脸部模型; 将所述个性化3D脸部模型投影到所述第一面部图像和所述第二面部图像中的每一个; 以及基于投射个性化3D脸部模型的第一面部图像与投影个性化3D脸部模型的第二面部图像之间的纹理图案的差异来细化个性化3D脸部模型。

    METHOD OF EXTRACTING FEATURE OF INPUT IMAGE BASED ON EXAMPLE PYRAMID, AND FACIAL RECOGNITION APPARATUS
    17.
    发明申请
    METHOD OF EXTRACTING FEATURE OF INPUT IMAGE BASED ON EXAMPLE PYRAMID, AND FACIAL RECOGNITION APPARATUS 有权
    基于实施例PYRAMID的输入图像特征提取方法和面部识别装置

    公开(公告)号：US20160078283A1

    公开(公告)日：2016-03-17

    申请号：US14817389

    申请日：2015-08-04

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Wonjun HWANG ,  Wonjun KIM ,  Sungjoo SUH ,  Jungbae KIM ,  Jaejoon HAN

    IPC: G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/00288 ,  G06K9/6244 ,  G06K9/6271

    Abstract: At least one example embodiment discloses a method of extracting a feature of an input image. The method includes constructing an example pyramid including at least one hierarchical level based on stored example images, generating a codebook in each of the at least one hierarchical level, calculating a similarity between the codebook and the input image, and extracting a feature of the input image based on the similarity.

    Abstract translation: 至少一个示例性实施例公开了一种提取输入图像的特征的方法。 该方法包括基于存储的示例图像构建包括至少一个层级的示例金字塔，在至少一个层级中的每一层生成码本，计算码本和输入图像之间的相似度，以及提取输入的特征 基于相似度的图像。

    METHOD AND APPARATUS FOR PROCESSING IMAGES
    18.
    发明申请
    METHOD AND APPARATUS FOR PROCESSING IMAGES 有权
    用于处理图像的方法和装置

    公开(公告)号：US20150269417A1

    公开(公告)日：2015-09-24

    申请号：US14641787

    申请日：2015-03-09

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Wonjun KIM ,  Sungjoo SUH ,  Jaejoon HAN

    IPC: G06K9/00 ,  G06T3/00

    CPC classification number: G06K9/00275 ,  G06K9/4642 ,  G06K9/6232

    Abstract: A method and apparatus for processing an image is disclosed, wherein the apparatus for processing the image may set blocks in an input image, perform an orthogonal transform on pixel values in the blocks, obtain orthogonal transform coefficients, and generate a resulting image by normalizing the obtained orthogonal transform coefficients.

    Abstract translation: 公开了一种用于处理图像的方法和装置，其中用于处理图像的装置可以在输入图像中设置块，对块中的像素值执行正交变换，获得正交变换系数，并通过归一化 获得正交变换系数。

    METHOD AND DEVICE WITH NEURAL NETWORK
    19.
    发明公开
    METHOD AND DEVICE WITH NEURAL NETWORK 审中-公开

    公开(公告)号：US20230252283A1

    公开(公告)日：2023-08-10

    申请号：US17982618

    申请日：2022-11-08

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jaeyun LEE ,  Kiho CHO ,  Jiwhan KIM ,  Sungun PARK ,  Jaejoon HAN

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: A processor-implemented method with a neural network includes: generating a first intermediate vector by applying a first activation function to first nodes in a first intermediate layer adjacent to an input layer among intermediate layers of the neural network; transferring the first intermediate vector to second nodes in a second intermediate layer adjacent to an output layer among the intermediate layers; generating a second intermediate vector by applying a second activation function to the second nodes; and applying the second intermediate vector to an output layer of the neural network, wherein the second activation function is determined by a first hyperparameter of which a multiplier of the second activation function is associated with an ascending slope of the second activation function and a second hyperparameter of which the multiplier is associated with a descending slope of the second activation function to fix a peak value of the second activation function.

    CONVOLUTIONAL NEURAL NETWORK (CNN) PROCESSING METHOD AND APPARATUS
    20.
    发明申请
    CONVOLUTIONAL NEURAL NETWORK (CNN) PROCESSING METHOD AND APPARATUS 有权

    公开(公告)号：US20230051648A1

    公开(公告)日：2023-02-16

    申请号：US17975837

    申请日：2022-10-28

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Jinwoo SON ,  Changyong SON ,  Jaejoon HAN ,  Chang Kyu CHOI

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.

Patent Agency Ranking