Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND SYSTEM OF NEURAL NETWORK OBJECT RECOGNITION FOR WARPABLE JERSEYS WITH MULTIPLE ATTRIBUTES
Document Type and Number:
WIPO Patent Application WO/2022/047662
Kind Code:
A1
Abstract:
A method and system of neural network object recognition for warpable jerseys with multiple attributes. A computer-implemented method of image processing, comprising: obtaining image data of clothing having varying visible attributes and visible identifiers on the outer surface of the clothing (302); synthetically warping a version of the image data to form warped images of synthetically warped clothing (304); and training a neural network to recognize the identifiers by using the warped images (306).

Inventors:
ZHENG HANG (CN)
LI QIANG (CN)
FANG LONGWEI (CN)
LI WENLONG (CN)
Application Number:
PCT/CN2020/113012
Publication Date:
March 10, 2022
Filing Date:
September 02, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
INTEL CORP (US)
ZHENG HANG (CN)
LI QIANG (CN)
FANG LONGWEI (CN)
LI WENLONG (CN)
International Classes:
G06N3/04
Foreign References:
CN109598270A2019-04-09
CN110033007A2019-07-19
CN111597846A2020-08-28
CN107273897A2017-10-20
CN107679533A2018-02-09
CN111428609A2020-07-17
US20200234083A12020-07-23
CN111445426A2020-07-24
CN111144498A2020-05-12
CN111046886A2020-04-21
Attorney, Agent or Firm:
NTD PATENT AND TRADEMARK AGENCY LTD. (CN)
Download PDF: