Systematic screening is crucial for the early diagnosis of sepsis. Detecting abnormal body temperature patterns can accurately predict sepsis before any other symptoms of infection. Therefore, we suggest using thermography as a non-invasive tool capable of continuously measuring body temperature patterns and detecting abnormalities. One such pattern is the temperature difference (ETD) between body extremities and the core temperature. In this paper, we propose a fully automated methodology for calculating core vs. extremity temperature difference based on the frontal and lateral view of the face. Thus, we present a fully automated model based on FCM clustering for inner and outer ear localisation and an efficient approach for tracking the tip of the nose and the inner corner of the eyes by using a mixture of Viola-Jones, KLT, and superpixel algorithms. The results demonstrate the robustness of these techniques in localising the four ROIs and in handling various poses and varying backgrounds.