Cross Processing Results     (training)     (back to index)

Size of test dataset: 35

Percentage of successful automatic results: 90%

Percentage of less successful automatic results: 10%

Comparison with Grabler09: Since this manipulation does not include any selections of labeled regions, the Grabler09 result is identical to the Average result.

Sample of successful results

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09
Sample of less successful results

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09

Input
Macro Result (Automatic)
Ground Truth
Average
Grabler09