FIELD: physics.
SUBSTANCE: invention relates to machine learning and, in particular, to transfer learning in the context of deep learning, as well as to methods of visual mineralogical analysis by classifying images of crystalline rocks based on additional features obtained as a result of vectorization of image segments. Method of analysing the mineralogical composition of crystalline rocks includes training a model of an artificial neural network and classifying the analysed sample of crystalline rock, with data collection subprocesses, during which the microscope or camera takes images of crystalline rocks, transferring the image to a computer for further processing; image preprocessing with vectorization of image segments to obtain additional features; training a model of a neural network ResNet using machine learning methods, and classification, which is performed in such a way that after training the model can classify new images. Model analyses additional features obtained as a result of vectorization and determines the mineral and its content.
EFFECT: high accuracy and speed of processing the obtained images, comparison and analysis results, ease of use.
2 cl, 8 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM FOR DIAGNOSING PATHOLOGICAL CHANGES IN PROSTATE BIOPSY SPECIMEN | 2021 |
|
RU2757256C1 |
METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE | 2022 |
|
RU2791415C1 |
METHOD FOR DETECTING CARDIOVASCULAR DISEASES BY ECG | 2024 |
|
RU2833175C1 |
METHOD FOR AUTOMATIC CLASSIFICATION OF X-RAY IMAGES USING TRANSPARENCY MASKS | 2019 |
|
RU2716914C1 |
HARDWARE-SOFTWARE COMPLEX DESIGNED FOR PROCESSING AERIAL PHOTOGRAPHS IN VISIBLE AND FAR INFRARED BAND FOR DETECTION, LOCALISATION AND CLASSIFICATION OF BUILDINGS OUTSIDE OF LOCALITIES | 2020 |
|
RU2752246C1 |
SYSTEM FOR RECOVERY OF ROCK SAMPLE THREE-DIMENSIONAL STRUCTURE | 2018 |
|
RU2718409C1 |
METHOD AND SYSTEM FOR AUTOMATED DETERMINATION OF CORE CHARACTERISTICS | 2024 |
|
RU2823446C1 |
METHOD FOR SELECTING IMAGES AT HIGH MAGNIFICATION USING NEURAL NETWORKS IN THE STUDY OF A BONE MARROW SMEAR AND A SYSTEM FOR IMPLEMENTING THE METHOD | 2022 |
|
RU2793060C1 |
METHOD AND SYSTEM FOR IDENTIFYING NEW GROWTHS ON X-RAY IMAGES | 2020 |
|
RU2734575C1 |
SOFTWARE AND HARDWARE COMPLEX DESIGNED FOR PROCESSING AEROSPACE IMAGE OF TERRAIN FOR PURPOSE OF DETECTION, LOCALIZATION AND CLASSIFICATION BY TYPE OF AVIATION AND LAND EQUIPMENT | 2021 |
|
RU2811357C2 |
Authors
Dates
2025-02-06—Published
2024-06-25—Filed