Skip to main content

Table 3 Comparison of the results using the sections separately and the random forest model

From: Improved wood species identification based on multi-view imagery of the three anatomical planes

 

Accuracy (± std)

TS

TS + TLS

TS + TLS + RLS

MVRF

500 × 500

0.75 (± 0.02)

0.86 (± 0.02)

0.89 (± 0.02)

0.95 (± 0.01)

500 × 500−OGRN

0.38 (± 0.02)

0.48 (± 0.02)

0.51 (± 0.02)

0.62 (± 0.03)

500 × 1000

0.71 (± 0.02)

0.85 (± 0.02)

0.87 (± 0.02)

0.91 (± 0.02)

1000 × 1000

0.56 (± 0.02)

0.62 (± 0.04)

0.66 (± 0.03)

0.66 (± 0.02)

  1. The first three columns respectively show the accuracy obtained using a random forest model trained on the LPQ features of the transverse images only (TS), a random forest model that uses the concatenation of LPQ features of the transverse and tangential sections (TS + TLS) and a random forest model that is obtained using the LPQ features from all three sections (TS + TLS + RLS)
Back to article page

Plant Methods

ISSN: 1746-4811