| Autor: |
Simi Venuji Renuka, Damodar Reddy Edla, Justin Joseph |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Journal of King Saud University: Computer and Information Sciences, Vol 34, Iss 10, Pp 9732-9744 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
1319-1578 |
| DOI: |
10.1016/j.jksuci.2021.12.005 |
| Popis: |
Post-processing algorithms like histogram equalization and its variants have been widely employed to enhance the contrast of Magnetic Resonance (MR) images. Objective metrics that can collectively reflect the improvement in contrast and inadvertent distortions are necessary to rate the quality of enhanced images. The objective of this paper is to formulate an objective statistic for rating the quality of contrast enhancement on MR images and to test the agreement of the proposed metric with the subjective fidelity ratings. An objective metric named Cumulative Quality of Contrast-Enhanced Images (CQCEI), for assessing the quality of contrast enhancement, especially the performance of the histogram equalization and its variants, on MR images is proposed. The CQCEI is formulated such that it collectively accounts for various aspects of image quality pertaining to the contrast enhancement, namely improvement in contrast, shift in mean brightness, saturation and noise-amplification. The CQCEI has shown good agreement with subjective fidelity ratings on contrast-enhanced MR images. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
