Open Access

ARTICLE

Optimizing Haze Removal: A Variable Scattering Approach to Transmission Mapping

Gaurav Saxena¹, Kiran Napte², Neeraj Kumar Shukla^3,4, Sushma Parihar^5,*

1 Department of Computer Science & Engineering, Jaypee University of Engineering and Technology, AB Road, Raghogarh, Guna, 473226, Madhya Pradesh, India
2 Department of Electronics & Telecommunication Engineering, Pimpri Chinchwad College of Engineering and Research, Ravet, Haveli, Pune, 412101, Maharashtra, India
3 Department of Electrical Engineering, College of Engineering, King Khalid University, P.O. Box 394, Abha, 61421, Saudi Arabia
4 Center for Engineering and Technology Innovations, King Khalid University, Abha, 61421, Saudi Arabia
5 Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University) (SIU), Pune, 412115, Maharashtra, India

* Corresponding Author: Sushma Parihar. Email:

(This article belongs to the Special Issue: Recent Advances in Signal Processing and Computer Vision)

Computer Modeling in Engineering & Sciences 2025, 144(2), 2307-2323. https://doi.org/10.32604/cmes.2025.067530

Received 06 May 2025; Accepted 14 July 2025; Issue published 31 August 2025

Abstract

The ill-posed character of haze or fog makes it difficult to remove from a single image. While most existing methods rely on a transmission map refined through depth estimation and assume a constant scattering coefficient, this assumption limits their effectiveness. In this paper, we propose an enhanced transmission map that incorporates spatially varying scattering information inherent in hazy images. To improve linearity, the model utilizes the ratio of the difference between intensity and saturation to their sum. Our approach also addresses critical issues such as edge preservation and color fidelity. In terms of qualitative as well as quantitative analysis, experimental outcomes show that the suggested framework is more effective than the currently used haze removal techniques.

---

Keywords

---