IDENTIFICATION OF MICROOBJECTS BASED ON BRIGHTNESS AND HISTOLOGICAL CHARACTERISTICS OF THE IMAGE

I. Jumanov, R. Safarov, O. Djumanov

Samarqand davlat universiteti ilmiy tadqiqotlar axborotnomasi · 2025-yil

Annotatsiya

A methodology and mechanisms for optimizing the processes of identifying, recognizing, and classifying microobjects have been developed using statistical, dynamic, brightness, and histological characteristics of image structure components. Tools for merging image models, multi-level segmentation, filtering, transformation, and aligning the laser image processing zone with the CAD model are proposed. Tools for multi-level segmentation, filtering based on Sobel, Prewitt, and Canny operators, and aligning the image processing zone with the CAD model are proposed. Algorithms for extracting object contours in the image using a boundary detector in the transverse direction to each CAD model vector are developed. The width and straightness of structural object boundaries, local defects, and control and synchronization parameters of vision system components for the medical diagnosis of chest diseases were determined. A mechanism for suppressing pulse interference and noise was implemented using various filtering methods, preserving object boundaries and small-scale details. Estimates of identification errors due to non-stationarity and inadequate approximation of the image contour were obtained. A software package for identifying, recognizing, and classifying images of micro-objects was developed.

Maqola ma’lumotlari
MualliflarI. Jumanov, R. Safarov, O. Djumanov
JurnalSamarqand davlat universiteti ilmiy tadqiqotlar axborotnomasi
Nashr sanasi2025-06-01
Jild5
Son1
Betlar88-97
DOI10.59251/2181-3973.2025.v1.138.1.3589

Samarqand davlat universiteti ilmiy tadqiqotlar axborotnomasi jurnalidan boshqa maqolalar

Samarqand davlat universiteti ilmiy tadqiqotlar axborotnomasi — barcha maqolalar