Recognition images of broken window glass

Oleksandr Derevyanchuk; Hanna Kravchenko; Yaroslav Derevianchuk; Vasyl Tomash

doi:10.1117/12.3012995

5 January 2024 Recognition images of broken window glass

Oleksandr Derevyanchuk, Hanna Kravchenko, Yaroslav Derevianchuk, Vasyl Tomash

Proceedings Volume 12938, Sixteenth International Conference on Correlation Optics; 129381C (2024) https://doi.org/10.1117/12.3012995
Event: International Conference Correlation Optics (COR 2023), 2023, Chernivtsi, Ukraine

Abstract

A method for recognizing images of broken window glass has been developed, the basis of which is the analysis of the orientation of the contours of glass cracks on a digital image. Contours in the images are highlighted by the fast-acting methods of Sobel or Canny. The obtained contours of the image depend slightly on the lighting conditions, which makes it possible to reliably detect cracks on the glass image. The orientation of image contours is determined based on the mD matrix of contour orientations, which records the sum of image contour values for each pixel within the dimensions of the matrix. For the matrix mD, discrete central moments and eccentricity SEC are calculated, which describes the degree of contour orientation. Based on the calculated eccentricity values, the presence of broken or unbroken glass in the image is determined. The program for recognizing the image of broken glass was developed in the Python language using the Google Colab cloud service. The initial images of the glass are read from video cameras or from graphic files. Contours are binarized using the Otsu method. Experimental testing of the developed program showed correct recognition of images of broken or unbroken glass. The developed program can be useful for monitoring the state of glass surfaces in vehicles and in various premises, for example, in educational institutions.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Oleksandr Derevyanchuk, Hanna Kravchenko, Yaroslav Derevianchuk, and Vasyl Tomash "Recognition images of broken window glass", Proc. SPIE 12938, Sixteenth International Conference on Correlation Optics, 129381C (5 January 2024); https://doi.org/10.1117/12.3012995

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
4 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Glasses

Matrices

Windows

Pattern recognition

Image processing

Video

Visualization

Show All Keywords

Keywords/Phrases

Search In:

Publication Years