Face Recognition as a Biometrics Approach Using Thermal Images

Biometrics is a technology used for measuring and analyzing a person's unique characteristics. Making a secure biometric system is not as easy as it might appear. The word biometrics is very often used as a synonym for the perfect security. Human Biometrics is now moving towards thermal imaging. Thermal imaging is simply the technique of using the heat given off by an object to produce an image of it. A thermal image provides more accurate information than the visual image. Hence a novel approach to face recognition based on thermal imaging is implemented here. The thermogram of the human face was captured from an infrared camera. In this work, an effective method to extract the thermal pattern of the human face using thermal images is presented. Thermal pattern of the human face is obtained by implementing the image processing techniques. Segmentation of human face from the rest of the image is the fundamental step in this process. After the face segmentation, the noise in the thermal image is removed using an appropriate standard filter. Then the morphological operations such as opening operation and top-hat method are performed on the image. From the result of the top-hat segmentation method, the features such as three quantitative distance measures are selected and compared with different subjects. Thirty volunteers were involved in this experimental procedure.