Automatic Representation and Segmentation of Video Sequences via a Novel Framework Based on the D-EVM and Kohonen Networks

Table 3

Size of the 3D-EVMs generated for every cluster associated with the billiard video sequence under a SOM with 10 neurons.

Class	EVM size
0	2,352
1	10,364
2	13,604
3	866
4	4,434
5	4,552
6	6,614
7	18,520
8	14,194
9	1,254
Total	76,754