Fusion of Visual and Thermal Face Recognition Techniques: A Comparative Study

Acknowledgements First of all, I would like to thank all IRIS Lab members. I would like to thank my advisor, Dr. Mongi Abidi. His willingness to support my work and his guidance throughout my studies has allowed me to develop my skills as a face recognition researcher within a supportive team environment. Abstract This paper describes how fusion of visual and thermal face recognition can increase the overall performance of face recognition systems. Visual face recognition systems perform relatively reliably under controlled illumination conditions. Thermal face recognition systems are advantageous for detecting disguised faces or when there is no control over illumination. Thermal images of individuals wearing eyeglasses may result in poor performance since eyeglasses block the infrared emissions around the eyes, which are important features for recognition. With taking advantages of each visual and thermal image, the new fused systems can be implemented in collaborating low-level data fusion and high-level decision fusion. This paper contains a comparative analysis of visual, thermal and fused face recognition performance and provides a breakthrough for future intelligent face recognition capable of making decisions based on visual, thermal or fused images depending on different situations.