mlsanityData to 7 Oct 2026

A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends

arXiv 2209.06399 ↗First posted 14 Sep 2022cs.NE cs.AI cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Computer vision (CV) is a big and important field in artificial intelligence covering a wide range of applications. Image analysis is a major task in CV aiming to extract, analyse and understand the visual content of images. However, image-related tasks are very challenging due to many factors, e.g., high variations across images, high dimensionality, domain expertise requirement, and image distortions. Evolutionary computation (EC) approaches have been widely used for image analysis with significant achievement. However, there is no comprehensive survey of existing EC approaches to image analysis. To fill this gap, this paper provides a comprehensive survey covering all essential EC approaches to important image analysis tasks including edge detection, image segmentation, image feature analysis, image classification, object detection, and others. This survey aims to provide a better understanding of evolutionary computer vision (ECV) by discussing the contributions of different approaches and exploring how and why EC is used for CV and image analysis. The applications, challenges, issues, and trends associated to this research field are also discussed and summarised to provide further guidelines and opportunities for future research.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 18 of its 215 references that are in the map. First posted on arXiv 14 Sep 2022.

Builds on

18 of 215 references.

References · 18

  1. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  2. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  3. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  4. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  5. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  6. 2020NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Searchcited by 75
  7. 2017A Genetic Programming Approach to Designing Convolutional Neural Network Architecturescited by 59
  8. 2020Neural Architecture Transfercited by 59
  9. 2017Evolving Deep Convolutional Neural Networks for Image Classificationcited by 54
  10. 2018Automatically designing CNN architectures using genetic algorithm for image classificationcited by 48
  11. 2018Multi-objective Evolutionary Federated Learningcited by 42
  12. 2020Real-time Federated Evolutionary Neural Architecture Searchcited by 20
6 more
  1. 2019Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classificationcited by 11
  2. 2020Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithmcited by 9
  3. 2020Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learningcited by 7
  4. 2020Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classificationcited by 6
  5. 2021Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learningcited by 2
  6. 2022Automated Design of Salient Object Detection Algorithms with Brain Programmingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 0; 2026: 3.

9 papers.