An application of fractal image-set coding in facial recognition

Faces are complex patterns that often differ in only subtle ways. Face recognition algorithms have difficulty in coping with differences in lighting, cameras, pose, expression, etc. We propose a novel approach for facial recognition based on a new feature extraction method called fractal image-set encoding. This feature extraction method is a specialized fractal image coding technique that makes fractal codes more suitable for object and face recognition. A fractal code of a gray-scale image can be divided in two parts – geometrical parameters and luminance parameters. We show that fractal codes for an image are not unique and that we can change the set of fractal parameters without significant change in the quality of the reconstructed image. Fractal image-set coding keeps geometrical parameters the same for all images in the database. Differences between images are captured in the non-geometrical or luminance parameters – which are faster to compute. Results on a subset of the XM2VTS database are presented.

Assessing health risk associated with airborne polycyclic aromatic hydrocarbons by chemometrics and toxic equivalency factors

Some polycyclic aromatic hydrocarbons (PAHs) are ubiquitous in air and have been implicated as carcinogenic materials. Therefore, literature is replete with studies that are focused on their occurrence and profiles in indoor and outdoor air samples. However, because the relative potency of individual PAHs vary widely, health risks associated with the presence of PAHs in a particular environment cannot be extrapolated directly from the concentrations of individual PAHs in that environment. In addition, database on the potency of PAH mixtures is currently limited. In this paper, we have utilized multi-criteria decision making methods (MCDMs) to simultaneously correlate PAH-related health risk in some microenvironments to the concentration levels, ethoxyresorufin-O-deethylase (EROD) activity induction equivalency factors and toxic equivalency factors (TEFs) of PAHs found in those microenvironments. The results showed that the relative risk associated with PAHs in different air samples depends on the index used. Nevertheless, this approach offers a promising tool that could help identify microenvironments of concern and assist the prioritisation of control strategies.

2D-3D Face Recognition Based on PCA and Feature Modelling

Hybrid face recognition, using image (2D) and structural (3D) information, has explored the fusion of Nearest Neighbour classifiers. This paper examines the effectiveness of feature modelling for each individual modality, 2D and 3D. Furthermore, it is demonstrated that the fusion of feature modelling techniques for the 2D and 3D modalities yields performance improvements over the individual classifiers. By fusing the feature modelling classifiers for each modality with equal weights the average Equal Error Rate improves from 12.60% for the 2D classifier and 12.10% for the 3D classifier to 7.38% for the Hybrid 2D+3D clasiffier.