Skip to main content

Table 5 Performances of k-NN, SVM, and ANN classifiers reported in CV-based wood identification studies

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

References Database Image type #SP/#IMG Feature Classification rate (%)
k-NN SVMa ANN
Hu et al. [128] – Macro 28/2800 SIFT 77.3 87.5 90.2
Tou et al. [117] CAIRO Stereo 5/500 GLCM 63.6 – 72.8
Prasetiyo et al. [147] FRIM Stereo 25/2390 LBP 80.0 85.6 93.6
Wang et al. [148] ZAFU WS 24 Stereo 24/480 GLCM 87.5 91.7 –
Wang et al. [68] ZAFU WS 24 Stereo 24/481 HLAC with MMI 76.3 87.7 –
Souza et al. [52] – Stereo 64/1901 LBP – 98.1 96.5
Yadav et al. [192] UFPR Micro 25/500 1st Stat. with Coiflet DWT – 65.2 92.2
Hwang et al. [73] XDD Micro 39/1557 SIFT 84.3 95.4 –
Kobayashi et al. [48] XDD Micro 18/2406 SIFT, CC 95.3 93.1 –
  1. #SP number of species, #IMG number of images, k-NN k-nearest neighbors, SVM support vector machine, ANN artificial neural network, Stereo stereogram, Micro micrograph, Macro macroscopic image, MMI mask matching image, 1st Stat first order statistic features, DWT discrete wavelet transform, CC connected component labelling
  2. aLinear kernel SVM classifier
Back to article page

Plant Methods

ISSN: 1746-4811