WHO has reported that an estimated 1.4 billion people worldwide have high blood pressure, but only 14% have it under control. Blood pressure monitoring using a non-contact measurement technique helps this problem. The methods of non-contact blood pressure measurements using facial thermal images obtained by a thermography device have been studied. The previous study constructed a general model of resting blood pressure estimation using independent components of facial thermal images. However, the optimization of a model such as hyperparameters or modeling methods was not enough to investigate. This study aimed to optimize the model for resting blood pressure estimation using facial thermal images.