Skip to main content

Table 6 Classification of pre-processed models on the basis of edge detection

From: Activity landscape image analysis using convolutional neural networks

CollectionRFSVMMetric
CannySobelCannySobel
10.48 ± 0.000.50 ± 0.010.52 ± 0.010.57 ± 0.01Accuracy
0.48 ± 0.010.50 ± 0.010.52 ± 0.010.58 ± 0.01F1
0.23 ± 0.010.26 ± 0.010.28 ± 0.020.36 ± 0.02MCC
20.44 ± 0.010.50 ± 0.010.50 ± 0.020.56 ± 0.01Accuracy
0.45 ± 0.010.50 ± 0.010.50 ± 0.020.56 ± 0.01F1
0.16 ± 0.020.25 ± 0.020.25 ± 0.020.34 ± 0.02MCC
30.45 ± 0.010.49 ± 0.020.51 ± 0.020.56 ± 0.01Accuracy
0.46 ± 0.010.49 ± 0.020.52 ± 0.020.57 ± 0.01F1
0.18 ± 0.010.24 ± 0.020.27 ± 0.030.35 ± 0.02MCC
40.43 ± 0.010.54 ± 0.030.53 ± 0.040.60 ± 0.03Accuracy
0.44 ± 0.020.54 ± 0.030.54 ± 0.040.60 ± 0.03F1
0.16 ± 0.020.31 ± 0.050.30 ± 0.060.40 ± 0.04MCC
50.44 ± 0.020.50 ± 0.020.47 ± 0.030.55 ± 0.02Accuracy
0.44 ± 0.020.51 ± 0.020.49 ± 0.030.57 ± 0.02F1
0.16 ± 0.030.26 ± 0.040.21 ± 0.050.33 ± 0.03MCC
60.42 ± 0.010.50 ± 0.020.52 ± 0.030.56 ± 0.02Accuracy
0.42 ± 0.010.51 ± 0.030.52 ± 0.020.58 ± 0.02F1
0.13 ± 0.020.25 ± 0.040.28 ± 0.040.35 ± 0.03MCC
70.61 ± 0.010.66 ± 0.030.73 ± 0.020.74 ± 0.01Accuracy
0.63 ± 0.010.66 ± 0.030.73 ± 0.020.74 ± 0.01F1
0.42 ± 0.020.50 ± 0.040.59 ± 0.030.61 ± 0.01MCC