Comparative Study on Interaction of Form and Motion Processing Streams by Applying Two Different Classifiers in Mechanism for Recognition of Biological Movement

Table 1

The proposed comparison method recognition results revealed among previous human action recognition method accuracies (bio- or non-bioinspired) on KTH human action dataset.

Methods	Accuracy (%)	Years
Schüldt et al., [39]	71.72	2004
Niebles et al., [45]	83.33	2008
Jhuang et al., [42]	91.79	2007
Schindler and Van Gool [11]	92.79	2008
Wang and Huang [34]	91.29	2005
Zhang and Tao [43]	U-SFA: 86.67	2012
	S-SFA: 86.40
	D-SFA: 89.33
	SD-SFA: 93.87
Yousefi and Loo [32]	SNN: 86.46	2014
Proposed method	ELM: 96.5