Table 2 Comparison of Precision and Recall scores among K-means, K-medoids, and Reference binary masks

From: An unsupervised approach towards promptable porosity segmentation In laser powder bed fusion by segment anything

 

K-means prompts

K-medoids prompts

Reference binary masks prompts

 

Precision

Recall

Precision

Recall

Precision

Recall

Sample 3

0.86 ± 0.0007

0.48 ± 0.0016

0.86 ± 0.008

0.48 ± 0.0013

0.86 ± 0.0003

0.48 ± 0.001

Sample 4

0.29 ± 0.011

0.87 ± 0.01

0.23 ± 0.013

0.81 ± 0.007

0.34 ± 0.016

0.95 ± 0.017

Sample 5

0.85 ± 0.001

0.94 ± 0.0001

0.84 ± 0.0009

0.93 ± 0.0001

0.84 ± 0.0009

0.93 ± 0.0001

Sample 6

0.79 ± 0.001

0.63 ± 0.01

0.82 ± 0.0003

0.68 ± 0.01

0.84 ± 0.0016

0.75 ± 0.01

Back to article page