FIELD: computer engineering.
SUBSTANCE: invention relates to computer engineering and specifically to methods of recognizing handwritten text using neural networks. Method for neural network recognition of handwritten text data on images is that an image f of a text field of a document is input, the dimensions of which are known, wherein the image f in the RGB colour space containing the text field of the document is further considered, wherein the input image f is processed by the neural network method according to the following algorithm: the image f is supplied to the image preparation unit, where it is converted into a single-channel, and also reduced to height Hf; at the second stage, the pre-trained neural network extracts visual features from the prepared image, forming a feature map Mf, prediction unit with an attention mechanism iteratively decodes a feature map Mf, predicting symbols one by one based on previously predicted ones, wherein if the stop criterion is achieved or the number of iterations exceeds N, then the recognition ends, wherein the extraction of visual features and the prediction unit with an attention mechanism are components of the same neural network model.
EFFECT: high speed of processing, as well as the ability to process input images of arbitrary width.
4 cl, 5 dwg, 1 tbl
Title | Year | Author | Number |
---|---|---|---|
IMAGE RECOGNITION SYSTEM: BEORG SMART VISION | 2020 |
|
RU2777354C2 |
RECOGNITION OF EVENTS ON PHOTOGRAPHS WITH AUTOMATIC SELECTION OF ALBUMS | 2020 |
|
RU2742602C1 |
OPTICAL CHARACTER RECOGNITION BY MEANS OF COMBINATION OF NEURAL NETWORK MODELS | 2020 |
|
RU2768211C1 |
DISTRIBUTED LEARNING MACHINE LEARNING MODELS FOR PERSONALIZATION | 2018 |
|
RU2702980C1 |
METHOD AND SYSTEM FOR RETRIEVING NAMED ENTITIES | 2020 |
|
RU2760637C1 |
METHOD FOR NEURAL NETWORK CONTROL OF TEXT DATA ON DOCUMENT IMAGES | 2023 |
|
RU2806012C1 |
IDENTIFICATION OF FIELDS AND TABLES IN DOCUMENTS USING NEURAL NETWORKS USING GLOBAL DOCUMENT CONTEXT | 2019 |
|
RU2723293C1 |
HANDWRITING RECOGNITION USING NEURAL NETWORKS | 2020 |
|
RU2757713C1 |
METHOD FOR INTERACTIVE SEGMENTATION OF OBJECT ON IMAGE AND ELECTRONIC COMPUTING DEVICE FOR REALIZING SAID OBJECT | 2020 |
|
RU2742701C1 |
IMAGE PROCESSING METHOD WITH TRAINED NEURAL NETWORKS | 2021 |
|
RU2779281C1 |
Authors
Dates
2025-03-28—Published
2024-08-15—Filed