FIELD: image processing means.
SUBSTANCE: invention relates to digital image processing methods and can be used in intelligent X-ray classification systems. Result is achieved with a manual of automatic classification of X-ray images using transparency masks, which involves forming an X-ray digital image in form of an array of optical densities of the object, obtaining depth layers of the image by processing the original digital image with local filters unique for each layer, reducing the dimensionality of images in the deep layers using a technique of pooling (sub-sampling), formation of a space of informative features for a trained fully connected neural network from sub-sampled deep layers and classification of the obtained vector of informative features by means of a fully-connected neural network.
EFFECT: technical result consists in improvement of accuracy of recognition of areas of interest when analyzing graphic information.
8 cl, 12 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD OF RECOGNIZING SPEECH EMOTIONS USING 3D CONVOLUTIONAL NEURAL NETWORK | 2023 |
|
RU2816680C1 |
METHOD FOR DETECTING OBJECTS IN THE IMAGE OF THE PLAN-SCHEME OF THE CONSTRUCTION OBJECT | 2022 |
|
RU2785821C1 |
FUEL COMBUSTION MODES MONITORING SYSTEM BY MEANS OF TORCH IMAGES ANALYSIS USING CLASSIFIER BASED ON CONVOLUTIONAL NEURAL NETWORK | 2018 |
|
RU2713850C1 |
DEVICE FOR CREATION OF MULTIDIMENSIONAL VIRTUAL IMAGES OF HUMAN RESPIRATORY ORGANS AND METHOD FOR CREATION OF VOLUMETRIC IMAGES, USING DEVICE | 2021 |
|
RU2783364C1 |
PROCESSING AND ANALYSIS OF DATA ON COMPUTER-ASSISTED TOMOGRAPHY IMAGES | 2017 |
|
RU2667879C1 |
ARTIFICIAL NEURAL NETWORKS COMPRESSION SYSTEM BASED ON ITERATIVE APPLICATION OF TENSOR APPROXIMATIONS | 2019 |
|
RU2734579C1 |
SYSTEM FOR IDENTIFYING FRESH PRODUCTS FOR A RETAIL TRADE CASH TERMINAL | 2018 |
|
RU2769888C2 |
IMAGE GENERATORS WITH CONDITIONALLY INDEPENDENT PIXEL SYNTHESIS | 2021 |
|
RU2770132C1 |
TRAINING GAN (GENERATIVE ADVERSARIAL NETWORKS) TO CREATE PIXEL-BY-PIXEL ANNOTATION | 2019 |
|
RU2735148C1 |
METHOD OF AUTOMATIC ESTIMATE OF LCD DATA DISPLAY CORRECTNESS | 2007 |
|
RU2346331C1 |
Authors
Dates
2020-03-17—Published
2019-10-22—Filed