Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing.
Saved in:
| Title: | Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing. |
|---|---|
| Authors: | Ayoub, Abeer1 (AUTHOR) abeerayoub777@gmail.com, El-Shafai, Walid1,2 (AUTHOR) walid.elshafai@el-eng.menofia.edu.eg, El-Samie, Fathi E. Abd1,3 (AUTHOR) fathi_sayed@yahoo.com, Hamad, Ehab K. I.4 (AUTHOR) e.hamad@aswu.edu.eg, Rabaie, El-Sayed M.1 (AUTHOR) srabie1@yahoo.com |
| Source: | Multimedia Tools & Applications. May2025, Vol. 84 Issue 17, p18071-18093. 23p. |
| Subjects: | Image intensifiers, Light transmission, Noise control, Signal-to-noise ratio, Haze, Histograms |
| Abstract: | Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. The superior quality attained with the proposed technique confirms its effectiveness in improving the visual quality of images and videos. For both visible and NIR frames, the percentages of enhancement obtained with the proposed technique are 92.99% and 117.60%, respectively. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. The superior quality attained with the proposed technique confirms its effectiveness in improving the visual quality of images and videos. For both visible and NIR frames, the percentages of enhancement obtained with the proposed technique are 92.99% and 117.60%, respectively. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-024-19043-9 |
