FIELD: calculating; counting.
SUBSTANCE: invention relates to the computer equipment. Method of image processing by trained neural networks includes creation of computer system initial set of images, where each image from the source image set comprises rendering a text string; creating an augmented set of images by processing an initial set of images for adding to each image from the original set of images of at least one simulated emulation defect of the process of capturing an image; creating a training data sample comprising a plurality of pairs of images, wherein each pair of images comprises a first image selected from the original set of images, and a second image selected from the augmented set of images; and training, using a training data sample, a convolutional neural network for image processing; and use of one or more trained convolutional neural network to process one or more images.
EFFECT: technical result is higher efficiency of processing images.
20 cl, 10 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| TEACHING LANGUAGE MODELS USING TEXT CORPUSES CONTAINING REALISTIC ERRORS OF OPTICAL CHARACTER RECOGNITION (OCR) | 2019 |
|
RU2721187C1 |
| METHOD FOR PROCESSING IMAGES BY CONVOLUTIONAL NEURAL NETWORKS | 2020 |
|
RU2771442C1 |
| IMAGE PROCESSING METHOD WITH TRAINED NEURAL NETWORKS | 2021 |
|
RU2779281C1 |
| REPRODUCING AUGMENTATION OF IMAGE DATA | 2018 |
|
RU2716322C2 |
| EXTRACTION OF MULTIPLE DOCUMENTS FROM A SINGLE IMAGE | 2020 |
|
RU2764705C1 |
| DETECTING AND IDENTIFYING OBJECTS ON IMAGES | 2020 |
|
RU2726185C1 |
| IDENTIFICATION OF FIELDS ON AN IMAGE USING ARTIFICIAL INTELLIGENCE | 2018 |
|
RU2695489C1 |
| METHOD AND SYSTEM FOR SEARCHING GRAPHIC IMAGES | 2022 |
|
RU2807639C1 |
| DETECTING TEXT FIELDS USING NEURAL NETWORKS | 2018 |
|
RU2699687C1 |
| IMAGE PROCESSING METHOD, TRAINING METHOD AND APPARATUS | 2021 |
|
RU2773420C1 |
