Open Access

ARTICLE

Displacement Feature Mapping for Vehicle License Plate Recognition Influenced by Haze Weather

Mohammed Albekairi¹, Radhia Khdhir^2,*, Amina Magdich³, Somia Asklany^4,*, Ghulam Abbas⁵, Amr Yousef ^6,7

1 Department of Electrical Engineering, College of Engineering, Jouf University, Sakakah, 72388, Saudi Arabia
2 College of Computer and Information Sciences, Jouf University, Sakakah, 72388, Saudi Arabia
3 Department of Computer sciences, Applied College, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
4 Department of Computers and Information Technologies, College of Sciences and Arts Turaif, Northern Border University, Arar, 91431, Saudi Arabia
5 School of Electrical Engineering, Southeast University, Nanjing, 210096, China
6 Department of Electrical Engineering, University of Business and Technology, Jeddah, 21448, Saudi Arabia
7 Engineering Mathematics Department, Alexandria University, Lotfy El-Sied st. off Gamal Abd El-Naser, Alexandria, 11432, Egypt

* Corresponding Authors: Radhia Khdhir. Email: ; Somia Asklany. Email:

(This article belongs to the Special Issue: Machine Learning and Deep Learning-Based Pattern Recognition)

Computer Modeling in Engineering & Sciences 2025, 144(3), 3607-3644. https://doi.org/10.32604/cmes.2025.069681

Received 28 June 2025; Accepted 20 August 2025; Issue published 30 September 2025

Abstract

License plate recognition in haze-affected images is challenging due to feature distortions such as blurring and elongation, which lead to pixel displacements. This article introduces a Displacement Region Recognition Method (DR2M) to address such a problem. This method operates on displaced features compared to the training input observed throughout definite time frames. The technique focuses on detecting features that remain relatively stable under haze, using a frame-based analysis to isolate edges minimally affected by visual noise. The edge detection failures are identified using a bilateral neural network through displaced feature training. The training converges bilaterally towards the minimum edges from the maximum region. Thus, the training input and detected edges are used to identify the displacement between observed image frames to extract and differentiate the license plate region from the other vehicle regions. The proposed method maps the similarity feature between the detected and identified vehicle regions. This aids in leveraging the plate recognition precision with a high F1 score. Thus, this technique achieves a 10.27% improvement in identification precision, a 10.57% increase in F1 score, and a 9.73% reduction in false positive rate compared to baseline methods under maximum displacement conditions caused by haze. The technique attains an identification precision of 95.68%, an F1 score of 94.68%, and a false positive rate of 4.32%, indicating robust performance under haze-affected settings.

---

Keywords

---