FIELD: computer equipment.
SUBSTANCE: invention relates to the field of computer equipment. Method includes the steps of: collecting image data; position the probable region of the string of characters in the image; receiving preliminary information of a predetermined string of characters; obtaining binary image from the image; obtaining curve of the projection of the binary image; obtaining corresponding pattern of segmentation points based on the preliminary information of the character string; obtaining confidence levels of different positions in a probable region of a character string; determining the position with the highest degree of confidence as the optimal position of the segmentation; segmenting the probable region of the character string; performing character recognition in each of the areas of a single character.
EFFECT: technical result consists in increasing the efficiency of character recognition.
10 cl, 10 dwg
| Title | Year | Author | Number | 
|---|---|---|---|
| ATM MANAGEMENT SYSTEM AND METHOD | 2016 | 
 | RU2708422C1 | 
| METHOD OF RECOGNIZING BANKNOTES BASED ON STORAGE OF DUST IN SORTING AND A SORTER | 2015 | 
 | RU2643493C1 | 
| METHOD OF ASSESSING THE VALIDITY OF A DOCUMENT USING OPTICAL RECOGNITION OF TEXT ON THE IMAGE OF A ROUND IMPRESSION OF A PRINT / STAMP ON A DIGITAL IMAGE OF A DOCUMENT | 2020 | 
 | RU2750395C1 | 
| METHOD FOR RECOGNITION OF TEXT IN IMAGES OF DOCUMENTS | 2021 | 
 | RU2768544C1 | 
| METHOD AND DEVICE FOR TRAINING A FACE RECOGNITION MODEL AND A DEVICE FOR DETERMINING THE KEY POINT OF THE FACE | 2019 | 
 | RU2770752C1 | 
| METHOD AND SYSTEM FOR AUTOMATICALLY CHECKING PRESENCE OF A LIVING HUMAN FACE IN BIOMETRIC SAFETY SYSTEMS | 2005 | 
 | RU2316051C2 | 
| HANDWRITING RECOGNITION USING NEURAL NETWORKS | 2020 | 
 | RU2757713C1 | 
| METHOD OF RECOGNIZING A SYMBOL ON A BANKNOTE AND A COPROCESSOR FOR A COMPUTING SYSTEM OF A BANKNOTE PROCESSING DEVICE | 2019 | 
 | RU2707320C1 | 
| METHOD AND DEVICE FOR IMAGE SEGMENTATION | 2014 | 
 | RU2596580C2 | 
| CHARACTER RECOGNITION METHOD | 2008 | 
 | RU2390843C2 | 
Authors
Dates
2019-01-29—Published
2015-06-26—Filed