Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, AND A NEURAL NETWORK TRAINING METHOD
Document Type and Number:
WIPO Patent Application WO/2019/042139
Kind Code:
A1
Abstract:
A neural network training method, an image processing method, and an image processing apparatus for implementing image style transfer. The training method comprises: obtaining a first training input image and a second training input image (S10); inputting the first training input image to a neural network (S20); using the neural network to perform style transfer processing on the first training input image to obtain a training output image (S30); calculating a loss value of a parameter of the neural network by means of a loss function on the basis of the first training input image, the second training input image, and the training output image (S40); modifying the parameter of the neural network according to the loss value (S50); and when the loss value satisfies a preset condition, obtaining a trained neural network (S70), and when the loos value does not satisfy the preset condition, continuing to input the first training input image and the second training input image to repeat the training process above, wherein the loss function comprises a weight-to-bias ratio loss function.

Inventors:
LIU HANWEN (CN)
NAVARRETE MICHELINI PABLO (CN)
Application Number:
PCT/CN2018/100833
Publication Date:
March 07, 2019
Filing Date:
August 16, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BOE TECHNOLOGY GROUP CO LTD (CN)
International Classes:
G06N3/04; G06T11/00; G06V10/764; G06V10/776
Domestic Patent References:
WO2017021322A12017-02-09
Foreign References:
CN106847294A2017-06-13
CN106709532A2017-05-24
CN106952224A2017-07-14
CN106651766A2017-05-10
Other References:
See also references of EP 3678059A4
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF: