Hybrid enhancement algorithm for nailfold images with large fields of view.
Microvasc Res
; 146: 104472, 2023 03.
Article
em En
| MEDLINE
| ID: mdl-36572207
ABSTRACT
Collecting and analyzing human nailfold images is an important component of studying human microcirculation. However, the large-field-of-view and high-resolution nailfold images captured by research microscopes introduce issues such as uneven brightness, low imaging contrast, and unclear vascular contours. To overcome these issues, this paper proposes a hybrid enhancement algorithm for nailfold images with large fields of view. First, adaptive histogram equalization with limited contrast (Clahe) is used to redistribute gray levels to enhance the brightness and contrast of images. Next, nonlocal means denoising (NL-means) is used to remove the noise amplified by Clahe algorithm. Finally, unsharp masking (Usm) is used to enhance the edge contour information of nailfold blood vessels. Comparing the enhanced images reveals that the hybrid enhancement algorithm improves the brightness and contrast of the nailfold image, makes the nailfold vessel contour more obvious, and the image noise continues to remain small, and it obtains the best visual effect. It is superior to other algorithms in terms of objective indicators and subjective evaluation.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Aumento da Imagem
Tipo de estudo:
Prognostic_studies
Limite:
Humans
Idioma:
En
Ano de publicação:
2023
Tipo de documento:
Article