FIELD: image data processing.
SUBSTANCE: invention relates to the field of computing technology, namely, to image processing means. Method for processing an image is applied to the sending node, wherein the method includes obtaining an image subject to processing, extracting features on the image subject to processing using the feature extraction layer contained in the convolutional neural network in order to obtain a first feature map, compressing the first feature map using the feature compression layer to obtain a second feature map, and sending the second feature map to the receiving node.
EFFECT: increase in the accuracy of processing images.
30 cl, 14 dwg
Title | Year | Author | Number |
---|---|---|---|
DETECTING TEXT FIELDS USING NEURAL NETWORKS | 2018 |
|
RU2699687C1 |
METHOD AND DEVICE FOR AUTONOMOUS AUTHENTICATION OF A PERSON | 2017 |
|
RU2697638C1 |
TEXT RECOGNITION USING ARTIFICIAL INTELLIGENCE | 2017 |
|
RU2691214C1 |
SYSTEM AND METHOD FOR ARTIFICIAL NEURAL NETWORK INVARIANT TO TRANSFERRING | 2017 |
|
RU2656990C1 |
METHOD OF BIOMETRIC AUTHENTICATION OF A USER AND A COMPUTING DEVICE IMPLEMENTING SAID METHOD | 2018 |
|
RU2697646C1 |
METHOD FOR ISOLATING AND CLASSIFYING BLOOD CELL TYPES USING DEEP CONVOLUTION NEURAL NETWORKS | 2019 |
|
RU2732895C1 |
IMAGE PROCESSING SYSTEM AND METHOD USING DEEP NEURAL NETWORKS | 2018 |
|
RU2743931C1 |
METHOD AND ELECTRONIC DEVICE FOR DETECTING THREE-DIMENSIONAL OBJECTS USING NEURAL NETWORKS | 2021 |
|
RU2776814C1 |
METHOD AND DEVICE FOR DETERMINING A PERSON'S POSTURE, DEVICE AND DATA CARRIER | 2019 |
|
RU2773232C1 |
SYSTEMS AND METHODS OF SEGMENTING IMAGE USING CONVOLUTION NEURAL NETWORK | 2017 |
|
RU2720070C1 |
Authors
Dates
2022-06-03—Published
2021-04-08—Filed