FIELD: physics.
SUBSTANCE: input text-containing image is obtained. The page sub-image is determined on the text-containing image. The vertical perspective of the page sub-display is corrected. The contour lines are created to display text lines of the page sub-image. The text line curving models are created for the page sub-images. The text lines of the resulting image-containing text are straightened out, using the text line curving model.
EFFECT: reducing errors when recognizing a text.
21 cl, 72 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM OF PREPARING TEXT-CONTAINING IMAGES TO OPTICAL RECOGNITION OF SYMBOLS | 2016 |
|
RU2628266C1 |
AUTOMATED DETERMINATION AND CUTTING OF NON-SINGULAR CONTOUR OF A PICTURE ON AN IMAGE | 2017 |
|
RU2680765C1 |
METHOD AND SUBSYSTEM OF DETERMINING DIGITAL IMAGES OF FRAGMENTS CONTAINING DOCUMENTS | 2016 |
|
RU2626661C1 |
METHOD AND SYSTEM FOR DETERMINING EXPANDED CONTOURS ON DIGITAL IMAGES | 2016 |
|
RU2628172C1 |
METHOD AND SYSTEM FOR CONVERTING SCREENSHOT INTO METAFILE | 2013 |
|
RU2534005C2 |
METHOD FOR RECOGNITION OF TEXT IN IMAGES OF DOCUMENTS | 2021 |
|
RU2768544C1 |
AUTOMATED METHODS AND SYSTEMS OF IDENTIFYING IMAGE FRAGMENTS IN DOCUMENT-CONTAINING IMAGES TO FACILITATE EXTRACTION OF INFORMATION FROM IDENTIFICATED DOCUMENT-CONTAINING IMAGE FRAGMENTS | 2016 |
|
RU2647670C1 |
DOCUMENT IMAGE CURVATURE ELIMINATING | 2016 |
|
RU2621601C1 |
SYSTEM AND METHOD FOR SCANNING AND COPYING | 2004 |
|
RU2368091C2 |
OPTICAL CHARACTER RECOGNITION OF DOCUMENTS WITH NON-PLANAR REGIONS | 2019 |
|
RU2721186C1 |
Authors
Dates
2017-11-20—Published
2016-12-06—Filed