Article Sidebar
Published:
Nov 2, 2022DOI:
10.4314/njt.v41i3.19Keywords:
Article Details
Copyright belongs to the Faculty of Engineering, University of Nigeria, Nsukka, Nigeria
The contents of the articles are the sole opinion of the author(s) and not of NIJOTECH.
NIJOTECH allows open access for distribution of the published articles in any media so long as whole (not part) of articles are distributed.
A copyright and statement of originality documents will need to be filled out clearly and signed prior to publication of an accepted article. The Copyright form can be downloaded from https://www.nijotech.com/downloads/COPYRIGHT%20FORM.pdf while the Statement of Originality is in Statement of Originality.pdf (nijotech.com)
For articles that were developed from funded research, a clear acknowledgement of such support should be mentioned in the article with relevant references. Authors are expected to provide complete information on the sponsorship and intellectual property rights of the article together with all exceptions.
It is forbidden to publish the same research report in more than one journal.
Main Article Content
The effects of camera focus and sensor exposure on accuracy using computer vision
Abstract
As industrial camera become smarter, due to the increase in supporting algorithms, so the quality of data produced offers higher precision and accuracy of industrial inspection operations. This paper aims to focus on the accurate effect of camera focus on a calibration process under the influence of different sensor exposure and degrees of focus. A computer vision methodology is used to determine the effects of different sensor exposures and at different degrees of camera focus. Endocentric and telecentric lenses are used to acquire images, and a comparative analysis was achieved using the least square method. A sample of 2176 images was used to generate the population for analysis. The analysis showed that the human eye cannot visually determine a hundred percent focus of an image. This means that it is difficult to determine when an image is 100% focused from when it is 95% focused. The result from the experiment showed that as the camera focus tends towards 100% the calibration error decreases, with a minimum calibration error of 0.06 pixels, leading to the conclusion that the developed method achieved a calibration error accuracy with the most effective camera sensor exposure and the camera focus.
