Combining the Improved RGB Water-Filling Algorithm With Penumbra Removal Technique for Shadow Removal From Digitized Images
This study proposes a novel and highly efficient approach for the comprehensive removal of shadows from digitized images that is applicable to a broad spectrum of image types, from document scans to natural scenes. The proposed method introduces an RGB water-filling algorithm specifically designed t...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10942598/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study proposes a novel and highly efficient approach for the comprehensive removal of shadows from digitized images that is applicable to a broad spectrum of image types, from document scans to natural scenes. The proposed method introduces an RGB water-filling algorithm specifically designed to address soft shadows, optimized with matrix operations and a streamlined processing workflow that substantially enhance the computational efficiency over existing methods. This improved efficiency facilitates real-time applications such as vision systems in automated guided vehicles, which often contend with shadow interference in natural environments. In addition to soft shadows, the proposed method addresses hard shadows, which can severely degrade the image quality and leave residual shadow boundaries that are difficult to eliminate using conventional techniques. To overcome this, the proposed method combines the RGB water-filling algorithm with the penumbra removal technique that not only removes shadow boundaries but also reconstructs the underlying image background. A comparative analysis demonstrates that the proposed method significantly reduces the root mean squared error (RMSE) by 70% and the processing time by 99%, while achieving the highest peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM), outperforming previous approaches for both soft and hard shadow removal. |
|---|---|
| ISSN: | 2169-3536 |