Title:
MODEL TRAINING METHOD, WATERMARK TEXT RECOGNITION METHOD, AND RELATED DEVICE
Document Type and Number:
WIPO Patent Application WO/2023/246402
Kind Code:
A1
Abstract:
Provided in the present application are a model training method, a watermark text recognition method, and a related device. The training method comprises: acquiring watermark style information and background style information, wherein the watermark style information is used for indicating a content style of a visible-watermark character, and the background style information is used for indicating a content style of a background picture; generating a watermark image set according to a combination of the watermark style information and the background style information, wherein the watermark image set comprises a plurality of images with visible watermarks; pixelating the watermark images in the watermark image set, extracting pixel values in pixel blocks as training samples, using visible watermarks, which correspond to the watermark images, as sample labels, and combining the training samples with sample labels corresponding thereto, so as to generate a training data set; and constructing a bidirectional recurrent neural network model, and calling the training data set to train the bidirectional recurrent neural network model, so as to obtain a model, which meets a training termination condition, as a watermark restoration model, wherein the watermark restoration model is used for restoring visible-watermark characters in the images.
Inventors:
SUN WEIDI (CN)
GUO FENG (CN)
SU XIAODONG (CN)
GUO FENG (CN)
SU XIAODONG (CN)
Application Number:
PCT/CN2023/095674
Publication Date:
December 28, 2023
Filing Date:
May 23, 2023
Export Citation:
Assignee:
BEIJING VOLCANO ENGINE TECH CO LTD (CN)
International Classes:
G06V30/19; G06N3/02; G06T5/00; G06T7/00
Foreign References:
| CN111160335A | 2020-05-15 | |||
| CN113887438A | 2022-01-04 | |||
| CN110097044A | 2019-08-06 | |||
| CN110969052A | 2020-04-07 | |||
| CN112419135A | 2021-02-26 | |||
| US20220130019A1 | 2022-04-28 |
Attorney, Agent or Firm:
SINOTALEN ATTORNEYS AT LAW (CN)
Download PDF: