Deep Learning vs. Traditional Computer Vision
By Niall O' Mahony, Sean Campbell, A. Carvalho, S. Harapanahalli, Gustavo Adolfo Velasco-Hernández, L. Krpalkova, Daniel Riordan, Joseph Walsh. Computer Vision Conference, 2019
1,050 citations recorded by the source corpus.
Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/92e4ef5575f3f22f3f22526cd1fdfd2d0397d094
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ehsan Khodapanah Aghdam
- Nader Tavvaf
- Edward A. Fox
- Dorit Merhof
- Reza Azad
- Joseph Paul Cohen
- Atlas Haddadi Avval
- Sanaz Karimijafarbigloo
Citations in the corpus
- Natural Language Processing Advancements By Deep Learning: A Survey (2020, background): “enable deep learning, one of the most appealing approaches in the NLP domain [2], [3], [5], especially given that deep learning has already demonstrated superior performance in adjoining fields like Computer Vision [6]–[10] and Speech Recognition [11]–[13].”
- Medical Image Segmentation Review: The Success of U-Net (2022, background): “The key factor that made them able to win the challenge was the availability of huge annotated data (CNN can learn comparatively better than the classical machine learning approach on large datasets [84], [85]).”