FIELD: computer technology.
SUBSTANCE: system for structured image recognition, using neural networks, contains: a module of data-assembling and distribution of received images; a module of determination of image page numbers; a module of image distortion elimination; a module of image separation and data marking for training a neural network; a module of algorithmic conversion and recognition by a neural network composition; a module of quality increasing and conversion of recognized values; a module of recognized value verification; a module of value assembly and final image formation; an integration module of unloading of formed data arrays from databases; a module of collection of document processing data and key indicator maintenance.
EFFECT: increase in the quality of structured image recognition.
3 cl, 2 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR NEURAL NETWORK RECOGNITION OF HANDWRITTEN TEXT DATA ON IMAGES | 2024 |
|
RU2837308C1 |
| METHOD FOR RECOGNISING CHEMICAL INFORMATION FROM IMAGES OF DOCUMENT AND SYSTEM FOR IMPLEMENTATION THEREOF | 2021 |
|
RU2774665C1 |
| METHOD FOR IMAGE PROCESSING USING ADAPTIVE TECHNOLOGIES BASED ON NEURAL NETWORKS AND COMPUTER VISION | 2020 |
|
RU2744769C1 |
| OPTICAL CHARACTER RECOGNITION BY MEANS OF COMBINATION OF NEURAL NETWORK MODELS | 2020 |
|
RU2768211C1 |
| TEXT RECOGNITION USING ARTIFICIAL INTELLIGENCE | 2017 |
|
RU2691214C1 |
| HANDWRITING RECOGNITION USING NEURAL NETWORKS | 2020 |
|
RU2757713C1 |
| METHOD AND SYSTEM FOR RECOGNIZING INFORMATION CONSTITUTING TRADE SECRET | 2024 |
|
RU2841161C1 |
| METHOD AND SYSTEM FOR SUPPORTING MEDICAL DECISION MAKING USING MATHEMATICAL MODELS OF PRESENTING PATIENTS | 2017 |
|
RU2703679C2 |
| METHOD FOR OPTICAL RECOGNITION OF TEXT LINES BASED ON FULL-CONVOLUTIONAL ANN, QUASI-SYMBOLOGY AND DYNAMIC PROGRAMMING | 2024 |
|
RU2837307C1 |
| METHOD FOR GENERATING MATHEMATICAL MODELS OF A PATIENT USING ARTIFICIAL INTELLIGENCE TECHNIQUES | 2017 |
|
RU2720363C2 |
