Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Student works
  4. Image correlation and data analysis applied to surface texture microscopy
 
master thesis

Image correlation and data analysis applied to surface texture microscopy

Majoor, Colin  
June 30, 2023

In this report we aim to analyze the moved volume from height profiles obtained before and after a strip drawing test. The goal is to determine whether a correlation exists between the pressure applied during the test and the volume moved or removed. We also aim to create a versatile data analysis tool for further investigation by Novelis. Eight crucial processing steps were implemented on the images, including inclination correction, surface height alignment, line detection, and moved volume normalization, in an effort to make them comparable within and between sets of images. Although a certain number of images had to be discarded due to stitching issues and difficulties in finding a correct homography at higher pressures, a significant percentage of them could be salvaged using line detection and match point randomization. The lack of sufficient data across different samples has made conclusive results difficult to obtain. For now it seems that a correlation exists between the pressure and the moved volume, but Novelis is actively working to add more data so that stronger conclusions can be drawn. The developped tool for data analysis will allow them to continue investigating any correlations with minimal user intervention as the dataset grows.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

Master_project_report_MAJOOR.pdf

Type

Main Document

Version

Accepted version

Access type

openaccess

License Condition

CC BY

Size

5.8 MB

Format

Adobe PDF

Checksum (MD5)

21472064387cf4059f520c8c142ad2b5

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés