Skip to main content

Table 2 Simulation setup for the different sampling methods

From: Automatic hand phantom map generation and detection using decomposition support vector machines

 

Sampling methods

RS and SS

MPS (pooling size = \(p \times q\))

# Training data sets per phantom map model

100

\(100 \times p \times q\)

# Testing data sets per phantom map model

10,000

Number of phantom maps in each database

 Phantom map database

Type

Number of phantom map images

 # Generated phantom maps

Complete 5

100

Complete 10

100

Incomplete 5

100

Incomplete 10

100

 # Transformed reported phantom map images

Reported (original)

5

Rotation

72 \(\times \) 5

Scaling

10 \(\times \) 5

Shearing

20 \(\times \) 5

Translation

10 \(\times \) 5

Barrel or pin cushion

20 \(\times \) 5