UO‘K 004.932.2 CANNY DETEKTORI PARAMETRLARINI TASVIRDAGI SHOVQIN BAHOSI ASOSIDA AVTOMATIK TANLASH

Authors

  • Nigora Murodjon qizi Tillashayxova Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti magistranti Author

Keywords:

Canny detektori, parametrlarni avtomatik tanlash, shovqinni baholash, Gauss filtri, bo‘sag‘a, kontrast, F1-o‘lchov

Abstract

Canny detektorining aniqligi Gauss filtri parametri va ikki bo‘sag‘aning tanlanishiga kuchli bog‘liq. Maqolada bu parametrlarni har bir tasvir uchun avtomatik aniqlaydigan qoida taklif etilgan. Silliqlash parametri Immerkær usuli bilan baholangan shovqin darajasidan, yuqori bo‘sag‘a esa silliqlangan tasvir gradientining 98-persentili va shovqin hosil qiladigan gradient sathidan aniqlanadi. Qoida koeffitsiyentlari alohida kalibrlash to‘plamida tanlandi. Etalon konturli sintetik tasvirlarda o‘tkazilgan tajribalar optimal parametrlar shovqin darajasiga bog‘liq ravishda o‘zgarishini ko‘rsatdi. Kontrast va shovqin turlicha bo‘lgan 20 ta sharoitda taklif etilgan qoida o‘rtacha F1 = 0,917 natija berdi. Bu ko‘rsatkich qat’iy standart parametrlar uchun 0,604 ni, kalibrlangan qat’iy parametrlar uchun 0,908 ni tashkil etdi.

Downloads

Index links

Google Scholar Zenodo OpenAIRE BASE OpenAlex Semantic Scholar DataCite

Published

2026-11-21

Issue

Section

Articles

How to Cite

UO‘K 004.932.2 CANNY DETEKTORI PARAMETRLARINI TASVIRDAGI SHOVQIN BAHOSI ASOSIDA AVTOMATIK TANLASH. (2026). Sharq Falsafasi, 11, 30-37. https://reandpub.uz/sharq-falsafasi/article/view/1620

References

Canny J. A computational approach to edge detection // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 1986. – Vol. PAMI-8, No. 6. – P. 679–698.

Beknazarova S., Tillashayxova N. A comparative analysis of baseline and contour-based image segmentation methods // Digital Transformation and Artificial Intelligence. – 2024. – Vol. 2, No. 4. – P. 95–99.

Ziou D., Tabbone S. Edge detection techniques – an overview // Pattern Recognition and Image Analysis. – 1998. – Vol. 8, No. 4. – P. 537–559.

Otsu N. A threshold selection method from gray-level histograms // IEEE Transactions on Systems, Man, and Cybernetics. – 1979. – Vol. 9, No. 1. – P. 62–66.

Immerkær J. Fast noise variance estimation // Computer Vision and Image Understanding. – 1996. – Vol. 64, No. 2. – P. 300–302.

Arabboev M., Begmatov Sh., Puziy A. A comprehensive review of contour extraction models: classical and AI-based approaches // Sovremennye innovatsii, sistemy i tekhnologii. – 2024. – Vol. 4, No. 4. – P. 157–175.

Mamatov N., Niyozmatova N., Jalelova M., Samijonov A., Samijonov B. A hybrid algorithm for contour thinning in image processing // Journal of Communications Software and Systems. – 2025. – Vol. 21, No. 1. – P. 23–33.

Martin D., Fowlkes C., Tal D., Malik J. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics // Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV). – 2001. – Vol. 2. – P. 416–423.

Bradski G. The OpenCV Library // Dr. Dobb’s Journal of Software Tools. – 2000. – Vol. 25, No. 11. – P. 120–125.