To evaluate the classifiers performance, sensitivity, specificity, positive predictive value (PPV), negative predictive
value (NPV) and accuracy were used. All these measures can be calculated based on four values: true positive (TP),
number of images correctly classified as motorcycles; false positive (FP), the number of images wrongly classified as
motorcycles; false negative (FN), the number of images wrongly classified as non-motorcycles and true negative (TN),
the number of images correctly classified as non-motorcycles. Those values are defined in table 1.