Laplacian and gaussian pyramid based multiscale fusion for nighttime image enhancement.
Saved in:
| Title: | Laplacian and gaussian pyramid based multiscale fusion for nighttime image enhancement. |
|---|---|
| Authors: | Singh, Pallavi1 (AUTHOR) swati.pals327@gmail.com, Bhandari, Ashish Kumar1 (AUTHOR) bhandari.iiitj@gmail.com |
| Source: | Multimedia Tools & Applications. May2025, Vol. 84 Issue 15, p15527-15551. 25p. |
| Subjects: | Image intensifiers, Image fusion, Image processing, Reflectance, Lighting, Image enhancement (Imaging systems) |
| Abstract: | We present a streamlined and effective fusion-based approach for enhancing images with low illumination, utilizing a combination of well-established image processing approaches. Initially, we utilize an illumination estimation algorithm relying on morphological closing to decompose a given image into a reflectance image as well as an illumination image. Subsequently, we define two inputs indicating luminance improvement as well as contrast enhancement, achieved by applying the sigmoid function as well as adaptive histogram equalization to the initially decomposed illumination. By designing two weights derived from these inputs, we generate an adjusted illumination through multi-scale fusion, combining the derived inputs with their respective weights. By employing an appropriate weighting as well as fusion strategy, we integrate the benefits of various methods to generate the adjusted illumination. The ultimate enhanced image is acquired by compensating for the adjusted illumination back into the reflectance. Through this synthesis, the improved image embodies a balance between enhancing details, improving local contrast, and preserving the natural appearance of the image. In the suggested fusion-based framework, images captured under various conditions of weak illumination, such as backlighting, non-uniform illumination, as well as nighttime scenarios, can be improved. Extensive experimentation has demonstrated that the proposed approach delivers comparable or superior performance when compared to state-of-the-art competing techniques, as evidenced by both qualitative as well as quantitative evaluations. Furthermore, this includes a comprehensive overview of different quality evaluation approaches for enhanced images, along with discussions comparing various algorithms. Lastly, the present research progress is summarized, with potential future research directions are proposed. [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: | We present a streamlined and effective fusion-based approach for enhancing images with low illumination, utilizing a combination of well-established image processing approaches. Initially, we utilize an illumination estimation algorithm relying on morphological closing to decompose a given image into a reflectance image as well as an illumination image. Subsequently, we define two inputs indicating luminance improvement as well as contrast enhancement, achieved by applying the sigmoid function as well as adaptive histogram equalization to the initially decomposed illumination. By designing two weights derived from these inputs, we generate an adjusted illumination through multi-scale fusion, combining the derived inputs with their respective weights. By employing an appropriate weighting as well as fusion strategy, we integrate the benefits of various methods to generate the adjusted illumination. The ultimate enhanced image is acquired by compensating for the adjusted illumination back into the reflectance. Through this synthesis, the improved image embodies a balance between enhancing details, improving local contrast, and preserving the natural appearance of the image. In the suggested fusion-based framework, images captured under various conditions of weak illumination, such as backlighting, non-uniform illumination, as well as nighttime scenarios, can be improved. Extensive experimentation has demonstrated that the proposed approach delivers comparable or superior performance when compared to state-of-the-art competing techniques, as evidenced by both qualitative as well as quantitative evaluations. Furthermore, this includes a comprehensive overview of different quality evaluation approaches for enhanced images, along with discussions comparing various algorithms. Lastly, the present research progress is summarized, with potential future research directions are proposed. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-024-19594-x |
