a b s t r a c tThis paper presents techniques designed to minimise the number of states which are explored during subgraph isomorphism detection. A set of advanced topological node features, calculated from nneighbourhood graphs, is presented and shown to outperform existing features. Further, the pruning effectiveness of both the new and existing topological node features is significantly improved through the introduction of strengthening techniques. In addition to topological node features, these strengthening techniques can also be used to enhance application-specific node labels using a proposed novel extension to existing pruning algorithms. Through the combination of these techniques, the number of explored search states can be reduced to near-optimal levels.

No abstract

Many Face Recognition techniques focus on 2D-2D comparison or 3D-3D comparison, however few techniques explore the idea of cross-dimensional comparison. This paper presents a novel face recognition approach that implements cross-dimensional comparison to solve the issue of pose invariance. Our approach implements a Gabor representation during comparison to allow for variations in texture, illumination, expression and pose. Kernel scaling is used to reduce comparison time during the branching search, which determines the facial pose of input images. The conducted experiments prove the viability of this approach, with our larger kernel experiments returning 91.6%-100% accuracy on a database comprised of both local data, and data from the USF HumanID 3D database.

Water is difficult environment for a wireless communications during swimming. A novel swimmer feedback system to enable consistent swimming pace consists of a ring of eight green LEDs which transmits information from a wrist mounted accelerometer using frequency shift keying (FSK) and on-off keying (OOK). The receiver on the goggles used an integrated detector preamplifier (IDP). The percentage of received optical data was determined for different positions for the swimmer's hand in different swimming styles (Freestyle, breaststroke, backstroke and butterfly). The system was evaluated in air and water to evaluate the preferred arm position and LED for communications. The stroke rate was determined using a 3-axis accelerometer and the interpretative firmware is different for each swimming style. One or more LEDs will be switched on during the cycle to achieve a maximum link performance. This system can be employed in pacing swimmers in both pool and open water swimming. I.