知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

36 records (took 0.017 seconds)

    CONVOLUTIONAL NEURAL NETWORK TUNING SYSTEMS AND METHODS
    21.
    发明申请
    CONVOLUTIONAL NEURAL NETWORK TUNING SYSTEMS AND METHODS 审中-公开

    公开(公告)号：US20190087729A1

    公开(公告)日：2019-03-21

    申请号：US15706930

    申请日：2017-09-18

    Applicant: Intel Corporation

    Inventor： Seok-Yong Byun ,  Byungseok Roh ,  Minje Park ,  Byoungwon Choe

    IPC: G06N3/08 ,  G05B13/02 ,  G06N3/04

    Abstract: Systems and methods are provided that tune a convolutional neural network (CNN) to increase both its accuracy and computational efficiency. In some examples, a computing device storing the CNN includes a CNN tuner that is a hardware and/or software component that is configured to execute a tuning process on the CNN. When executing according to this configuration, the CNN tuner iteratively processes the CNN layer by layer to compress and prune selected layers. In so doing, the CNN tuner identifies and removes links and neurons that are superfluous or detrimental to the accuracy of the CNN.

    Face recognition using gradient based feature analysis
    24.
    发明授权
    Face recognition using gradient based feature analysis 有权
    使用基于梯度的特征分析进行人脸识别

    公开(公告)号：US09384385B2

    公开(公告)日：2016-07-05

    申请号：US14535133

    申请日：2014-11-06

    Applicant: Intel Corporation

    Inventor： Minje Park ,  Hyungsoo Lee ,  Hongmo Je ,  Tae-Hoon Kim ,  Yeongjae Cheon ,  Taesup Kim

    IPC: G06K9/00 ,  G06K9/52 ,  G06T7/00 ,  G06K9/62 ,  G06K9/46

    CPC classification number: G06K9/3275 ,  G06K9/00248

    Abstract: Computer-readable storage media, computing devices and methods are discussed herein. In embodiments, a computing device may be configured to perform facial recognition based on gradient based feature extractions of images of faces. In embodiments, the computing device may be configured to determine directional matching patterns of the images from the gradient based feature extraction and may utilize these directional matching patterns in performing a facial recognition analysis of the images of faces. Other embodiments may be described and/or claimed.

    Abstract translation: 本文讨论了计算机可读存储介质，计算设备和方法。 在实施例中，计算设备可以被配置为基于面部图像的基于梯度的特征提取来执行面部识别。 在实施例中，计算设备可以被配置为从基于梯度的特征提取来确定图像的方向匹配模式，并且可以在对面部图像执行面部识别分析时利用这些方向匹配模式。 可以描述和/或要求保护其他实施例。

    Method, Apparatus and Computer-Readable Recording Medium for Managing Images in Image Database
    25.
    发明申请
    Method, Apparatus and Computer-Readable Recording Medium for Managing Images in Image Database 有权
    用于管理图像数据库中的图像的方法，装置和计算机可读记录介质

    公开(公告)号：US20140136566A1

    公开(公告)日：2014-05-15

    申请号：US14129328

    申请日：2013-02-15

    Applicant: INTEL CORPORATION

    Inventor： Tae Hoon Kim ,  Minje Park

    IPC: G06F17/30

    CPC classification number: G06F17/30277 ,  G06F17/30247 ,  G06F17/3028

    Abstract: Managing images in an image database is described, comprising: when a query image is input, performing a match to determine whether an image similar to the query image exists within the database by comparing the images stored in the database with the query image; and if the image similar to the query image is a recognized image, providing at least one image in an image group to which the recognized image belongs and information thereon as a result, and if the image similar to the query image is an unrecognized image, providing at least one image in an image group to which the unrecognized image belongs as a result. When at least one image of the image group including the image similar to the query image is a recognized image, information on the corresponding recognized image is assigned to the images in the image group and provided as a result.

    Abstract translation: 描述管理图像数据库中的图像，包括：当输入查询图像时，通过将存储在数据库中的图像与查询图像进行比较，执行匹配以确定与查询图像相似的图像是否存在于数据库内; 并且如果与查询图像类似的图像是识别的图像，则在所识别的图像所属的图像组中提供至少一个图像，并且在其上提供关于其的信息，并且如果与查询图像相似的图像是无法识别的图像， 作为结果，在不能识别的图像所属的图像组中提供至少一个图像。 当包括与查询图像相似的图像的图像组的至少一个图像是识别的图像时，关于相应的识别图像的信息被分配给图像组中的图像并作为结果。

    Methods and apparatus to convert images for computer-vision systems
    29.
    发明授权
    Methods and apparatus to convert images for computer-vision systems 有权

    公开(公告)号：US11335106B2

    公开(公告)日：2022-05-17

    申请号：US16649566

    申请日：2017-11-29

    Applicant: Intel Corporation

    Inventor： Tae-Hoon Kim ,  Minje Park

    IPC: G06K9/00 ,  G06V20/80 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V10/143

    Abstract: An example computer-vision system to convert images includes an image converter (112) to convert a near infrared light first image (202) to form a visible light image (206), and to update a coefficient of the image converter (112) based on a difference (214), an object recognizer (102) to recognize an object (208) in the first visible light image (206), and an object recognition analyzer (210) to determine the difference (214) between the object (208) recognized in the first visible light image (206) and an object (212) associated with the near infrared light image (202).

Patent Agency Ranking