Vision-based deformation inspection system for automotive glass using Hough circle detectors
Abstract The production of automotive glass with minimal deformation and optical flaws is crucial for the safe operation of vehicles on which the glass is installed. The conventional method of inspecting vehicle glass during the manufacturing process relies on human inspectors to visually examine the glass, rendering it prone to human error. This study proposes a frequency reconstruction method established on computer vision to automatically detect deformation flaws in automotive glass. To quantify the deformation of an outwardly curving glass product, we use the digital imaging of a known standard pattern with base dots through a sample to capture a transmitted and reflected deformation image. We then apply the circular Hough transform voting scheme to find the peak points of the base dots in parameter space and reconstruct an image with the base dots of the captured image. The binary testing image is subtracted from the binary reconstructed image to obtain a binary difference image that displays the detected deformation areas. Experimental outcomes suggest that the proposed approach reaches a high 82.76% probability of correctly discriminating deformation flaws and a low 1.14% probability of incorrectly investigating regular regions as deformation flaws on transmitted appearances of automotive glass.
| Main Authors: | , , |
|---|---|
| Format: | Digital revista |
| Language: | English |
| Published: |
Universidad Nacional Autónoma de México, Instituto de Ciencias Aplicadas y Tecnología
2023
|
| Online Access: | http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1665-64232023000400598 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|