GENERATION OF MARKING OF DOCUMENT IMAGES FOR TRAINING SAMPLE Russian patent published in 2018 - IPC G06T1/00 

Abstract RU 2668717 C1

FIELD: data processing.

SUBSTANCE: invention relates to creating a markup of a document image. Example of the method includes identifying key points in each of a plurality of images; adding each of the plurality of images to one or more clusters, adding includes adding key points to one or more indexes associated with the clusters, where the minimum number of one or more key points corresponds to the key points in the indexes; analysis of each of the cluster images as a candidate image for generation by generating markup along the document boundaries that exists in the candidate image; verification of markup by comparing the markup with the boundaries of the document shown on several other images of the cluster; and selecting a candidate image as a reference image if the markup has been verified more than a predetermined number of times; and detecting the markup of the document along the borders of the document present in the source image, using the reference image.

EFFECT: technical result consists in expanding the arsenal of document markup tools.

21 cl, 7 dwg

Similar patents RU2668717C1

Title Year Author Number
METHODS AND SYSTEMS FOR IDENTIFYING FIELDS IN A DOCUMENT 2020
  • Semenov Stanislav Vladimirovich
  • Lanin Mikhail Olegovich
RU2760471C1
AUTOMATED METHODS AND SYSTEMS OF IDENTIFYING IMAGE FRAGMENTS IN DOCUMENT-CONTAINING IMAGES TO FACILITATE EXTRACTION OF INFORMATION FROM IDENTIFICATED DOCUMENT-CONTAINING IMAGE FRAGMENTS 2016
  • Zagaynov Ivan Germanovich
  • Borin Pavel Valerievich
RU2647670C1
METHODS AND SYSTEMS FOR IDENTIFYING FIELDS IN A DOCUMENT 2021
  • Stanislav Semenov
RU2774653C1
DEVICE AND METHOD FOR RECOGNIZING CONTOURS OF AGRICULTURAL FIELDS USING DEEP LEARNING BASED ON REMOTE SENSING DATA 2021
  • Anokhin Aleksandr Leonidovich
  • Tskhaj Boris Vitalevich
  • Yarygin Andrej Mikhajlovich
  • Temin Lev Vladimirovich
RU2783296C1
TEXT RECOGNITION USING ARTIFICIAL INTELLIGENCE 2017
  • Orlov Nikita Konstantinovich
  • Rybkin Vladimir Yurevich
  • Anisimovich Konstantin Vladimirovich
  • Davletshin Azat Ajdarovich
RU2691214C1
IMAGE OBJECT CATEGORY RECOGNITION METHOD AND DEVICE 2014
  • Gan Yunchzhou
  • Den Chzhenpin
RU2648946C2
RETRIEVING FIELDS USING NEURAL NETWORKS WITHOUT USING TEMPLATES 2019
  • Stanislav Semenov
RU2737720C1
METHOD AND SYSTEM FOR SEARCHING GRAPHIC IMAGES 2022
  • Shulga Sergej Aleksandrovich
RU2807639C1
AUTOMATIC DETERMINATION OF SET OF CATEGORIES FOR DOCUMENT CLASSIFICATION 2018
  • Nikita Orlov
  • Konstantin Anisimovich
RU2701995C2
DETECTING "FUZZY" IMAGE DUPLICATES USING TRIPLES OF ADJACENT RELATED FEATURES 2015
  • Fedorov Sergey Mikhailovich
  • Kacher Olga Arnoldovna
RU2613848C2

RU 2 668 717 C1

Authors

Zagajnov Ivan Germanovich

Borin Pavel Valerevich

Dates

2018-10-02Published

2017-12-13Filed