Research Article

Infrared Thermal Image Gender Classifier Based on the Deep ResNet Model

Table 3

The Performance measures of the proposed IRT_ResNet models.

Net nameMetricsData 1 ratio (%)Data 2 ratio (%)All data ratio (%)

IRT_ResNet 18Precision969296.6
Recall949993.8
F-score95.395.795.2
Overall accuracy95.495.695.2
IRT_ResNet 50Precision969794.5
Recall8798.696
F-score91.597.895.3
Overall accuracy91.997.895.2
IRT_ResNet 101Precision859997.3
Recall97.794.397
F-score90.996.697.2
Overall accuracy90.296.797.2