Model training method and device, text image processing method, equipment and medium

CN121646808APending Publication Date: 2026-03-10BEIJING BOE TECH DEV CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-11-24
Publication Date
2026-03-10

Smart Images

  • Figure CN121646808A_ABST
    Figure CN121646808A_ABST
Patent Text Reader

Abstract

The invention provides a model training method and device, a text image processing method, computer equipment and a computer readable storage medium, and the method comprises the steps: obtaining a sample set, wherein the sample set comprises a plurality of sample groups; the sample group comprises an original image sample and an original text sample; performing mask processing on the original image sample and the original text sample to generate a mask image sample and a mask text sample; performing adversarial training on a generator and a discriminator by using the mask image sample and the mask text sample to obtain a target model; the generator comprises a feature extraction network and an output network, and the feature extraction network is used for performing feature extraction after performing information fusion on an input image and an input text of the generator; the output network is used for generating a recovered image according to an output result of the feature extraction network; the discriminator is used for judging whether the recovered image is consistent with the original text sample; the target model at least comprises a feature extraction network in the trained generator.
Need to check novelty before this filing date? Find Prior Art