| Autor: |
Ramanjaneyulu, R., Rajmohan, V., Thiruchelvam, V., Susiapan, Y. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 3161 Issue 1, p1-7, 7p |
| Abstrakt: |
This research aims to assess and compare the efficacy of two distinct image segmentation methodologies: the Novel Watershed algorithm and the Adaptive Thresholding approach. The objective is to enhance the precision of white blood cell (WBC) segmentation within microscopic images. The segmentation process employs the Novel Watershed algorithm, designated as group 1, encompassing a sample size of N=10. Simultaneously, the Adaptive Thresholding technique constitutes group 2, also with N=10 samples. The study maintains a pre-test power of 80%, alongside alpha and beta values of 0.05 and 0.2, and a 95% confidence interval. The entire process is executed using MATLAB software. The segmentation accuracy achieved by the Novel Watershed algorithm is 86%, mirroring the accuracy of the Adaptive Thresholding approach, which also yields an 86% accuracy rate. The disparity between these segmentation results is statistically significant, denoted by a significance value of p=0.002 (p<0.05), indicating an error-free outcome. The Novel Watershed algorithm distinctly outperforms the Adaptive Thresholding algorithm in augmenting the accuracy of white blood cell segmentation. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
