Document image self-annotation method, device, storage medium and electronic device

By performing tilt correction and optical flow field analysis on the document captured images, the inverse transformation annotation of document information is solved, and the problems of high labeling cost and low efficiency in the prior art are provided, and high-quality model training data and reliable annotation results are provided.

CN115482314BActive Publication Date: 2025-06-06BEIJING ORIENTAL SIHONG TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110606956.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-27
Publication Date
2025-06-06
Estimated Expiration
2041-05-27

Smart Images

  • Figure CN115482314B_ABST
    Figure CN115482314B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method, device, storage medium and electronic device for self-annotation of document images, which can realize self-annotation of document images, and the annotation results are reliable. The method includes: obtaining a document image and an original document image corresponding to the document image; performing tilt correction on the document content in the document image to obtain a corrected image; and determining the conversion relationship between the corrected image and the document image; based on the optical flow field between the original document image and the corrected image, and the conversion relationship, performing inverse transformation processing on the document information extracted from the original document image, and annotating the inversely transformed document information on the document image. It does not require a large amount of manpower, and ensures the integrity and clarity of the document image.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method and system for improving definition of text images

    CN102013094A

  • Camera-based document imaging

    CN102084378A