Artificial Intelligence in Computer Vision: Enabling Technologies and New Capabilities

DOI

10.2991/978-94-6239-823-8_3How to use a DOI?

Keywords

Machine Vision; Deep Learning; Convolutional Neural Networks; Vision Transformers; Transfer Learning; Engineering Education

Abstract

Machine vision has been reshaped over the past decade by the adoption of artificial intelligence, and by deep neural networks that learn visual features from data rather than relying on rules designed by hand. This paper reviews the principal AI technologies now employed in computer vision and examines how each has extended the capability of vision systems. It traces the shift from hand-crafted feature engineering to learned representations and surveys the main architecture families in current use: convolutional networks, detection and segmentation architectures, vision transformers, structured landmark representations, and generative and self-supervised approaches. It then examines the cross-cutting enablers that decide whether a method is practically usable: transfer learning, benchmark infrastructure, and deployment technologies including open exchange formats and model compression. Attention is paid to the consequences for higher education, where pretrained models running on commodity hardware have made practical machine vision teachable and reproducible in ordinary classrooms. The review concludes that the decisive contribution of AI has been less any single architecture than the emergence of a reusable ecosystem of pretrained models, portable runtimes, and shared benchmarks, and that the principal open challenges are now data cost, domain shift, interpretability, and the widening gap between frontier-scale models and deployable systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - László Árvai
PY  - 2026
DA  - 2026/11/04
TI  - Artificial Intelligence in Computer Vision: Enabling Technologies and New Capabilities
BT  - Proceedings of the Innovation in Engineering Education 2026 Conference (IEE 2026)
PB  - Atlantis Press
SP  - 19
EP  - 28
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-823-8_3
DO  - 10.2991/978-94-6239-823-8_3
ID  - Árvai2026
ER  -