Skip to main content

Table 4 Performances of major local features and textures for wood identification

From: Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review

References Database Image type #SP/#IMG CLS Classification rate (%)
Local features Textures
SIFT SURF ORB AKAZE GLCM LBP LPQ
Hu et al. [128] Macro 28/2800 ANN 90.2 63.8 85.7
Martins et al. [47] UFPR Micro 112/2240 SVM 88.5 89.1 4.1 66.3 86.7
Hwang et al. [74]a XDDb Micro 9/1019 SVM 79.2 42.2 63.6 61.6
  1. Macro macroscopic image, Micro micrograph, #SP number of species, #IMG number of images, CLS classifier, ANN artificial neural network, SVM support vector machine
  2. aF1 score was used as a performance metric
  3. bLauraceae wood dataset in the XDD database