EURASIP Journal on Image and Video Processing

Table 5 Results of proposed algorithm compared using four classifiers on CASIA dataset

From: A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection

Method	AUC	FPR	FNR (%)	Recall (%)	Accuracy (%)
M-class SVM	0.99	0.01	1.3	98.65	98.70
DT	0.98	0.02	2.1	97.90	97.90
LDA	0.99	0.01	1.8	98.15	98.20
KNN	0.98	0.02	1.9	98.05	98.10
EBT	0.97	0.07	7.3	93.55	92.70

Back to article page