Skip to main content
. 2021 May 24;21(11):3647. doi: 10.3390/s21113647

Table 2.

Comparison of different methods under the same typical dataset.

Reference Dataset Method Evaluation Metrics
Chavan et al. (2018) [30] Plant seedlings dataset [20] AgroAVNET (A hybrid model of AlexNet and VGGNET) Accuracy: 98.23%
Trong et al. (2021) [31] Yielding multi-fold training (YMufT) strategy and DNN; Min-class-max-bound procedure (MCMB); Resnet Accuracy: 97.18%
Xu et al. (2021) [32] Depthwise separable convolutional neural network, Xception Accuracy: 99.63%
Olsen et al. (2019) [21] Deepweeds [21] Dataset was classified with the ResNet-50 and Inception-v3 CNN models to establish a baseline level of performance for comparison. Accuracy: 95.1%
(Inception-v3)
Accuracy: 95.7%
(ResNet-50)
Ferreira et al. (2019) [33] Joint Unsupervised Learning of Deep Representations and Image Clusters (JULE) and Deep Clustering for Unsupervised Learning of Visual Features (DeepCluster) Precision: 95%
Hu et al. (2020) [34] GWN (Graph Weeds Net) Accuracy: 98.1%
Naresh et al. (2016) [35] Flavia [28] MLBP (Modified Local binary patterns) Accuracy: 97.55%
Mahajan et al. (2021) [36] Support vector machine with adaptive boosting Precision:95.85%
Yang C. Z. (2021) [37] MTD (multiscale triangle descriptor) and LBP-HF (local binary pattern histogram Fourier) Accuracy: 99.1%