Face recognition using infrared vision
|Authors:||Shoja Ghiass, Reza|
|Advisor:||Bendada, Abdelhakim; Maldague, Xavier|
|Abstract:||Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in the real world. While inherently insensitive to visible spectrum illumination changes, IR images introduce specific challenges of their own, most notably sensitivity to factors which affect facial heat emission patterns, e.g., emotional state, ambient temperature, etc. In addition, facial expression and pose changes are more difficult to correct in IR images because they are less rich in high frequency details which is an important cue for fitting any deformable model. In this thesis we describe a novel method which addresses these major challenges. Specifically, to normalize for pose and facial expression changes we generate a synthetic frontal image of a face in a canonical, neutral facial expression from an image of the face in an arbitrary pose and facial expression. This is achieved by piecewise affine warping which follows active appearance model (AAM) fitting. This is the first work which explores the use of an AAM on thermal IR images; we propose a pre-processing step which enhances details in thermal images, making AAM convergence faster and more accurate. To overcome the problem of thermal IR image sensitivity to the exact pattern of facial temperature emissions we describe a representation based on reliable anatomical features. In contrast to previous approaches, our representation is not binary; rather, our method accounts for the reliability of the extracted features. This makes the proposed representation much more robust both to pose and scale changes. The effectiveness of the proposed approach is demonstrated on the largest public database of thermal IR images of faces on which it achieves satisfying recognition performance and significantly outperforms previously described methods. The proposed approach has also demonstrated satisfying performance on subsets of the largest video database of the world gathered in our laboratory which will be publicly available free of charge in future. The reader should note that due to the very nature of the feature extraction method in our system (i.e., anatomical based nature of it), we anticipate high robustness of our system to some challenging factors such as the temperature changes. However, we were not able to investigate this in depth due to the limits which exist in gathering realistic databases. Gathering the largest video database considering some challenging factors is one of the other contributions of this research.|
|Document Type:||Thèse de doctorat|
|Open Access Date:||20 April 2018|
|Collection:||Thèses et mémoires|
All documents in CorpusUL are protected by Copyright Act of Canada.