Detekcija napak na materialih s periodično strukturo

KRUPIĆ, BILAL (author), Perš, Janez (mentor)

Razvili smo metodo strojnega vida, ki bi naj bila sposobna detektirati napake v materilalih, ki iskazujejo periodično strukturo. Metoda temelji na dvodimenzionalni Fourierjevi transformaciji. Naša osnovna predpostavka je, da pri Fourierjevi transformaciji slike vzorca, ki izkazuje periodično strukturo, dobimo veliko število vrhov, in majhno število vrhov, ko vzorec vsebuje napako. Vrhovi so zaznani z detektorjem MSER. Izhod detektorja MSER je število vrhov. Kot primer smo uporabili vzorce tekstila, v katere smo vnesli napake (cefranje, zbadanje, rezanje). Zajeli smo sistematično bazo slik, ter napake na tekstilnih vzorcih označili z zaključenimi poligoni. Na vsakem zaključenem poligonu smo izračunali očrtan pravokotnik, ki je bil vodilo, za izrez vsakega od vzorcev, ki smo jih uporabili za potrebe binarnega razvrščanja vzorcev na tiste brez napake in z napako. Za detekcijo napak smo kvalitativno ilustrirali delovanje detektorja napak, ki uporablja predstavljen razvrščevalnik ter metodo drsečega okna.

• Language: Slovenian
• Keywords: strojni vid, računalniški vid, tekstil, razvrščevanje, detekcija napak
• Work type: Bachelor thesis/paper
• Organization: FE - Faculty of Electrical Engineering
• Year: 2018
• PID: 20.500.12556/RUL-103535
• Publication date in RUL: 19.09.2018

KRUPIĆ, BILAL, 2018, Detekcija napak na materialih s periodično strukturo [online]. Bachelor’s thesis. [Accessed 23 March 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=103535

Secondary language

• Language: English
• Title: Detecting Defects in Materials That Exhibit Periodic Structure

Abstract

We have developed a machine vision method that will be able to detect errors in materials that show a periodic structure. The method is based on a two-dimensional Fourier transform. Our basic assumption is that the Fourier transformation of the image that exhibits a periodic structure results in a pattern which contains a large number of peaks. Conversely, it contains a small number of peaks when the sample contains a defect, which disrupts the periodic structure. The peaks are detected by the MSER detector. The output of the MSER detector is the number of peaks. To illustrate and evaluate the proposed method, we used textile samples in which we created defects (tearing, puncturing, cutting). We systematically collected a database of images, and marked the defects in textile patterns as polygons. For each polygon we calculated the bounding box that was used in sample extraction from images. Samples were classified to those without defect and those containing a defect. For the detection of defects, we have qualitatively illustrated the operation of the error detector using the presented classifier and the sliding window method.

• Keywords: machine vision, computer vision, textile, classification, defect detection