METHOD FOR DETERMINING DEFECTS IN THE IMAGE OF COMPOSITE PRODUCTS Russian patent published in 2023 - IPC G01N23/46 

Abstract RU 2807288 C1

FIELD: determining defects in the image of composite products.

SUBSTANCE: invention relates to a method for determining defects in the image of composite products. The technical result is achieved by uploading an image of the finished product and selecting areas for defect detection; by means of a trained deep neural network, each pixel is determined to belong to the "defect" or "no defect" class and a segmentation mask is obtained; post-processing is carried out, in which a segmentation mask and an image of the finished product are received at the input of the module and filtering is carried out assigned pixels to the "defect" class by the signs images of the finished product, namely the area and linear dimensions of connected areas of defect pixels, deviations of the average value of defect pixels from the average value of pixels in the area of defect detection, and also aggregate filtered pixels by the depth of the object and isolate volumetric defects from them; calculate the characteristics of the selected volumetric defects by measuring the linear dimensions of connected pixel areas defects, and classification of defects based on the measured linear dimensions of connected areas of pixels of defects.

EFFECT: technical result is to increase the accuracy of determining the defects of composite products.

8 cl, 3 dwg

Similar patents RU2807288C1

Title Year Author Number
METHOD OF PROCESSING IMAGES OF REMOTE EARTH PROBING USING A NEURAL NETWORK WITH A FINE FOR ACCURACY OF THE SEGMENTATION BOUNDARY 2019
  • Artemov Aleksei Valerevich
  • Burnaev Evgenii Vladimirovich
  • Bokhovkin Aleksei Konstantinovich
  • Volkhonskii Denis Alekseevich
RU2740736C1
SYSTEM AND METHOD FOR DETECTING PULMONARY PATHOLOGIES FROM X-RAY IMAGES 2023
  • Skvortsov Aleksandr Vadimovich
  • Khastiev Shamil Rinatovich
  • Novikov Andrei Andreevich
  • Karimov Ainur Fanovich
RU2840009C1
SYSTEM AND METHOD FOR DIAGNOSING PULMONARY PATHOLOGIES FROM X-RAY IMAGES 2023
  • Skvortsov Aleksandr Vadimovich
  • Khastiev Shamil Rinatovich
  • Novikov Andrei Andreevich
  • Karimov Ainur Fanovich
RU2840011C1
RECONSTRUCTION OF THE DOCUMENT FROM DOCUMENT IMAGE SERIES 2017
  • Loginov Vasilij Vasilevich
  • Zagajnov Ivan Germanovich
  • Karatsapova Irina Aleksandrovna
RU2659745C1
METHOD FOR DRYING FORMED RAW BRICK 2020
  • Smirnov Gennadii Vasilevich
  • Zamiatin Nikolai Vladimirovich
RU2742163C1
METHOD OF CONTROLLING CERAMIC ARTICLES DRYING 2020
  • Smirnov Gennadij Vasilevich
  • Zamyatin Nikolaj Vladimirovich
RU2738532C1
METHOD FOR DETERMINING FAULT POSITION BASED ON SEISMIC DATA 2022
  • Miftakhov Ruslan Fanisovich
  • Efremov Igor Ivanovich
  • Bazanov Andrej Konstantinovich
RU2783367C1
METHOD FOR PROCESSING COMPUTER TOMOGRAPHY IMAGES (CT IMAGES) 2023
  • Danilov Aleksej Nikolaevich
  • Yakovlev Andrej Vladimirovich
RU2812866C1
METHOD AND SYSTEM FOR DETECTION OF SPACE-OCCUPYING KIDNEY LESIONS ON COMPUTED TOMOGRAMS OF ABDOMINAL CAVITY 2024
  • Gevorkyan Tigran Gagikovich
  • Skvortsov Aleksandr Vadimovich
  • Stepanov Aleksandr Sergeevich
  • Drobot Natalya Tsyren-Dondokovna
  • Babarykina Valeriya Aleksandrovna
RU2839531C1
METHOD AND SYSTEM FOR MEASURING SIZE OF NEW GROWTHS INSIDE BODY DURING ENDOSCOPIC PROCEDURES BASED ON PROCESSING OF SERIES OF ENDOSCOPIC IMAGES IN AUTOMATIC MODE 2022
  • Zajtsev Pavel Anatolevich
  • Valik Andrej Vladimirovich
  • Kim Yana
  • Khajrullin Ravil Gabdullovich
  • Kulaev Konstantin Ivanovich
  • Vazhenin Andrej Vladimirovich
  • Privalov Aleksej Valerevich
RU2839240C2

RU 2 807 288 C1

Authors

Kremnev Ivan Aleksandrovich

Vorobev Ruslan Igorevich

Dates

2023-11-13Published

2022-11-24Filed