Thermal Facial Pattern Recognition for Personal Verification Using Fuzzy Cmac Model

This paper presents a novel personal verification system with thermal facial patterns using fuzzy neural network techniques. In contrast to traditional biometrics, the use of thermal technology removes two concerns in existing verification systems; they are: 1) the hygiene issue for verification systems that require physical contact (e.g., fingerprints) and, 2) variation in ambient illumination for visible-band camera verification system. In the proposed verification process, features extracted from thermal facial images are matched with trained fuzzy neural networks, in particular, the biologically inspired TSK-FCMAC, a fuzzy cerebellar model articulation controller (CMAC) based on the zero-ordered Takagi-Sugeno-Kang (TSK) fuzzy inference scheme. TSK-FCMAC is capable of performing localized online training with an effective fuzzy inference scheme. Preliminary simulations show that the proposed verification system is able to achieve an Equal Error Rate (EER) of 6.1% and the True Acceptance Rate (TAR) of above 86% for identification. The work in this paper shows that the thermal face patterns can provide a reasonable level of discriminating power, and has the potential to be used in the context of biometric applications especially when used in conjunction with other biometric modalities.