FIELD: physics.
SUBSTANCE: image is taken, its histogram is calculated, values of the histogram are converted to input arguments of a neural network and the output value of the neural network is calculated. The input arguments of the neural network used are normalised to the unit value of the histogram calculated with a given class interval. The brightness level is calculated as a linear function of the output value of the neural network. The neural network is trained using a learning set calculated on a given image base. The set of target values used is the brightness levels calculated for each image on the area of interest and scaled to the range of the neuron activation function of the output layer of the neural network.
EFFECT: high rate of processing a digital image.
6 cl, 5 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD OF ASSESSING QUALITY OF TELERADIOLOGICAL IMAGES | 2023 |
|
RU2815039C1 |
| METHOD OF PROCESSING MAGNETIC RESONANCE IMAGING IMAGES FOR GENERATING TRAINING DATA | 2023 |
|
RU2813480C1 |
| METHOD OF AUTOMATIC SEGMENTATION OF FLUOROGRAMM OF BREAST OF PATIENTS WITH PNEUMONIA | 2016 |
|
RU2629629C1 |
| DEVICE AND METHOD FOR DETERMINING THE PATHOLOGY OF THE CHEST ORGANS BASED ON X-RAY IMAGES | 2021 |
|
RU2782518C1 |
| METHOD AND DEVICE FOR DETERMINATION OF WEAR PART LOCATION ON WORKING TOOL IMAGE | 2016 |
|
RU2713684C2 |
| METHOD FOR AUTOMATIC CLASSIFICATION OF X-RAY IMAGES USING TRANSPARENCY MASKS | 2019 |
|
RU2716914C1 |
| DETECTING AND IDENTIFYING OBJECTS ON IMAGES | 2020 |
|
RU2726185C1 |
| DEVICE AND METHOD FOR ANALYSIS OF MEDICAL IMAGES | 2022 |
|
RU2806982C1 |
| DEVICE AND METHOD FOR DETERMINING BOUNDARIES OF PATHOLOGY ON MEDICAL IMAGE | 2022 |
|
RU2813938C1 |
| METHOD OF TRAINING DEEP NEURAL NETWORKS BASED ON DISTRIBUTIONS OF PAIRWISE SIMILARITY MEASURES | 2016 |
|
RU2641447C1 |
