Effect of Camera Choice on Image-Classification Inference
Article
Article Title | Effect of Camera Choice on Image-Classification Inference |
---|---|
ERA Journal ID | 211776 |
Article Category | Article |
Authors | Brown, Jason, Nguyen, Andy and Raj, Nawin |
Journal Title | Applied Sciences |
Journal Citation | 15 (1) |
Article Number | 246 |
Number of Pages | 24 |
Year | 2025 |
Publisher | MDPI AG |
Place of Publication | Switzerland |
ISSN | 2076-3417 |
Digital Object Identifier (DOI) | https://doi.org/10.3390/app15010246 |
Web Address (URL) | https://www.mdpi.com/2076-3417/15/1/246 |
Abstract | The field of image classification using Convolutional Neural Networks (CNNs) to predict the principal object in an image has seen many recent innovations. One aspect that has not been extensively explored is the effect of the camera employed to acquire images for inference. We investigate this by capturing comparable images of five drinking vessels using six cameras in various scenarios. We examine the classification ranking of object classes when these images are input to an independently pretrained Resnet-18 model based on the ImageNet-1k dataset. We find that the camera used can affect the top prediction of object class, particularly in scenarios with a more complex background. This is the case even when the cameras have similar fields of view. We also introduce a metric called selectivity, defined as the mean absolute difference between prediction probabilities of similar relevant object classes (such as cups and mugs). We show that the effect of the camera is largest when the selectivity of the pretrained model between these object classes is small. The effect of camera choice is also demonstrated quantitatively by examining Cohen’s Kappa (κ) statistic. Finally, we make recommendations on mitigating the effect of the camera on image-classification inference. |
Keywords | image classification; camera; prediction; inference; computer vision |
Article Publishing Charge (APC) Amount Paid | 0.0 |
Article Publishing Charge (APC) Funding | Other |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 400904. Electronic device and system performance evaluation, testing and simulation |
460304. Computer vision | |
Byline Affiliations | School of Engineering |
School of Mathematics, Physics and Computing |
https://research.usq.edu.au/item/zv1w1/effect-of-camera-choice-on-image-classification-inference
Download files
13
total views2
total downloads6
views this month0
downloads this month