Sistem za preverjanje napak na lesu : diplomsko delo

Udovič, Janez (author), Solina, Franc (mentor)

Namen diplomskega dela je predstavitev prototipa sistema za optično preverjanje napak na lesu, konkretno na bambusovih deščicah, namenjenih izdelavi parketa. Za optično zaznavanje napak smo uporabili barvne kamere The Imaging Source DFK 23G018, ki so z računalniškim sistemom povezane preko Ethernet kabla. Predstavljene so štiri metode za obdelavo posnetih slik. Prva metoda izmeri dimenzije in določi robove opazovanega objekta oziroma lesene deščice. Znotraj določenih robov delujejo metoda za iskanje lukenj na objektu, metoda za iskanje poškodb na objektu in pa metoda za določanje barvne skupine objekta. Za simuliranje pomikanja deščic vzdolž procesne linije skrbi koračni servomotor. V okviru našega diplomskega dela je opisano tudi delovanje in upravljanje s krmilnikom motorja.

• Language: Slovenian
• Keywords: optična kontrola, detekcija napak na lesu, računalniški vid, koračni motor, računalništvo, visokošolski strokovni študij, računalništvo in informatika, diplomske naloge
• Work type: Bachelor thesis/paper
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science
• Publisher: [J. Udovič]
• Year: 2015
• Number of pages: 41 str.
• PID: 20.500.12556/RUL-30694
• COBISS.SI-ID: 1536301507
• Publication date in RUL: 14.04.2015

UDOVIČ, Janez, 2015, Sistem za preverjanje napak na lesu : diplomsko delo [online]. Bachelor’s thesis. J. Udovič. [Accessed 31 March 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=30694

Secondary language

• Language: English
• Title: A system for visual control of wood imperfections

Abstract

The objective of this thesis is to present a prototype of an optical wood control system, concretely, an optical measurement system for bamboo boards intended for parquet flooring. We used The Imaging Source DFK 23G018 color cameras for optical detection and measurement. In this thesis we present four methods for processing the images of wooden boards. The first method finds the edges of the boards and measures individual dimensions. By knowing the exact position of the boards in the images, the remaining three methods detect holes in the boards and different kinds of imperfections and sort the boards into appropriate color groups. To simulate the control part of the process line we used a step actuator. The functionality and the management of the actuator are also explained.

• Keywords: optical measurement, wood imperfection detection, computer vision, step actuator, computer science, computer and information science, diploma