A Study on the Performance of Adaptive Neural Networks for Haze Reduction with a Focus on Precision

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

  • Ahmed Alshahir
  • Khaled Kaaniche
  • Ghulam Abbas
  • Paolo Mercorelli
  • Mohammed Albekairi
  • Meshari D. Alanazi

Visual clarity is significantly compromised, and the efficacy of numerous computer vision tasks is impeded by the widespread presence of haze in images. Innovative approaches to accurately minimize haze while keeping image features are needed to address this difficulty. The difficulties of current methods and the need to create better ones are brought to light in this investigation of the haze removal problem. The main goal is to provide a region-specific haze reduction approach by utilizing an Adaptive Neural Training Net (ANTN). The suggested technique uses adaptive training procedures with external haze images, pixel-segregated images, and haze-reduced images. Iteratively comparing spectral differences in hazy and non-hazy areas improves accuracy and decreases haze reduction errors. This study shows that the recommended strategy significantly improves upon the existing training ratio, region differentiation, and precision methods. The results demonstrate that the proposed method is effective, with a 9.83% drop in mistake rate and a 14.55% drop in differentiating time. This study’s findings highlight the value of adaptable neural networks for haze reduction without losing image quality. The research concludes with a positive outlook on the future of haze reduction methods, which should lead to better visual clarity and overall performance across a wide range of computer vision applications.

Original languageEnglish
Article number2526
JournalMathematics
Volume12
Issue number16
Number of pages25
DOIs
Publication statusPublished - 15.08.2024

Bibliographical note

Publisher Copyright:
© 2024 by the authors.

    Research areas

  • haze reduction, machine learning, neural networks, pixel distribution, region classification, training net
  • Engineering

DOI

Recently viewed

Researchers

  1. Marcus Erben

Activities

  1. Princeton University
  2. Authenticity in modelling test items
  3. It's Time to Talk About Time Shaping Competence: A Framework for Addressing “Time” in ESE
  4. A Framework for Text Analytics in Online Interventions
  5. Thomas Weise
  6. Presentation: Nexus of Housing and Migration
  7. Using the Method of Limits to Assess Comfortable Time Headways in Adaptive Cruise Control
  8. Micro and macro scale behavior of thermochemical materials in pure and composite forms for thermal storage applications
  9. Digital, open and collaborative: New teaching formats for times of crisis – and beyond?
  10. Evaluating the efficacy and cost-effectiveness of web-based prevention of major depression: Preliminary results.
  11. Workshop on Negotiation and Conflict Resolution at University of Amsterdam - UVA 2018
  12. "Crowds and Party" Reading Workshop with Jody Dean - 2019
  13. Methodological Assemblage - Experiences from an Interdisciplinary Project on Artists and Cities
  14. Knowledge of result versus elaborated feedback: Students‘ perception of feedback on a digital learning platform
  15. Integrating Time Aspects into the Assessment of Sustainable Resource Management
  16. Response to Philip Hogh: Suffering, Pain and the Idea of Progress
  17. Analyzing diary data: The relationships between activities and the individual mood level
  18. Theoretical Dimensions of Good Practices for Struggling Adolescent Readers
  19. Towards a sustainable use of indium – Relating technology options and governance interventions for dealing with indium criticality
  20. Podiumsdiskussion zu MEDEA
  21. Brush up zu KODE© und KODEX© 2011