In this paper, we propose a method of detecting nasal cavity location in far infrared images for non-contact determination of human breathing. Current non-contact methods for far infrared imaging assumed that the user's body is stationary. We apply the Viola-Jones' method to exactly detect regions that includes nasal cavities. 5,100 FIR images are collected to train our nasal cavity detector; we evaluate the number of false alarms and detection failures. The results show that proposed method can accurately detect nasal region from the front view of the face.