FIELD: image forming devices.
SUBSTANCE: present document discloses systems and methods for obtaining an image of at least part of a document and determining a plurality of division points dividing an image into potential segments; creating a graph of linear division (GLD), containing a plurality of vertices using a plurality of division points and a plurality of ribs connecting a plurality of vertices; identifying an GLD path having a quality metric value higher than a threshold value, where a path is selected from a plurality of GLD paths and comprises one or more ribs, and the quality metric value is output using a neural network which classifies each of the plurality of pixels of the image; as well as creation of one or more image blocks, where each of one or more units corresponds to the edge of the identified path and represents part of the image associated with the object type.
EFFECT: methods and systems of document segmentation are proposed.
20 cl, 10 dwg
Title | Year | Author | Number |
---|---|---|---|
SOFTWARE AND HARDWARE COMPLEX DESIGNED FOR PROCESSING AEROSPACE IMAGE OF TERRAIN FOR PURPOSE OF DETECTION, LOCALIZATION AND CLASSIFICATION BY TYPE OF AVIATION AND LAND EQUIPMENT | 2021 |
|
RU2811357C2 |
EXTRACTION OF MULTIPLE DOCUMENTS FROM A SINGLE IMAGE | 2020 |
|
RU2764705C1 |
METHOD, APPARATUS AND DEVICE FOR IMAGE SEGMENTATION | 2014 |
|
RU2577188C1 |
METHOD FOR VISUALIZING A 3D PORTRAIT OF A PERSON WITH ALTERED LIGHTING AND A COMPUTING DEVICE FOR IT | 2021 |
|
RU2757563C1 |
RECONSTRUCTION OF THE DOCUMENT FROM DOCUMENT IMAGE SERIES | 2017 |
|
RU2659745C1 |
SYSTEM AND METHOD FOR DIAGNOSING PATHOLOGIES OF PARANASAL SINUSES BY X-RAY IMAGES | 2023 |
|
RU2825958C1 |
SEGMENTATION OF MULTICOLUMN DOCUMENT | 2014 |
|
RU2647671C2 |
SYSTEM AND METHOD FOR DETERMINING PATHOLOGIES OF PARANASAL SINUSES BY X-RAY IMAGES | 2023 |
|
RU2825519C1 |
METHOD OF PROCESSING IMAGES OF REMOTE EARTH PROBING USING A NEURAL NETWORK WITH A FINE FOR ACCURACY OF THE SEGMENTATION BOUNDARY | 2019 |
|
RU2740736C1 |
METHOD AND SYSTEM FOR REMOTE CLOTHING SELECTION | 2020 |
|
RU2805003C2 |
Authors
Dates
2019-08-15—Published
2018-10-23—Filed