Classic versus deep learning approaches to address computer vision challenges

TL;DR

This paper compares classic and deep learning methods in computer vision, highlighting their respective strengths and limitations in applications like edge detection and image registration.

Contribution

It provides a comparative analysis of classic and deep learning algorithms, offering insights into their suitability for different computer vision tasks.

Findings

Deep learning methods outperform classic algorithms in accuracy and development time.

Classic algorithms are more resource-efficient and transparent.

The choice between approaches depends on specific application needs.

Abstract

Computer vision and image processing address many challenging applications. While the last decade has seen deep neural network architectures revolutionizing those fields, early methods relied on 'classic', i.e., non-learned approaches. In this study, we explore the differences between classic and deep learning (DL) algorithms to gain new insight regarding which is more suitable for a given application. The focus is on two challenging ill-posed problems, namely faint edge detection and multispectral image registration, studying recent state-of-the-art DL and classic solutions. While those DL algorithms outperform classic methods in terms of accuracy and development time, they tend to have higher resource requirements and are unable to perform outside their training space. Moreover, classic algorithms are more transparent, which facilitates their adoption for real-life applications. As both classes of approaches have unique strengths and limitations, the choice of a solution is clearly application dependent.