Skip to main content

Table 3 Performances of GLCM, LBP, and LPQ texture features 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 Classifier Classification rate (%)
GLCM LBP LPQ
Prasetiyo et al. [147] CAIRO Stereo 25/2390 ANN 89.6 93.6
Martins et al. [47] UFPR Micro 112/2240 SVM 55.3 79.3
Kobayashi et al. [66] XCT 6/240 k-NN 98.3 99.5
Cavalin et al. [115] UFPR Micro 112/2240 SVM 80.7 88.5 91.5
Paula Filho et al. [62] UFPR Macro 41/2942 SVM 56.0 68.2 61.8
Martins et al. [95] UFPR Micro 112/2240 SVM 4.1 66.3 86.7
Yadav et al. [122] UFPR Micro 75/1500 SVM 79.9 93.5
da Silva et al. [71] RMCA Micro 77/1221 k-NN (k = 1) 85.0 87.4
  1. Stereo stereogram, Macro macroscopic image, Micro micrograph, XCT X-ray computed tomographic image, #SP number of species, #IMG number of images, ANN artificial neural network, SVM support vector machine, k-NN k-nearest neighbors