Force Field Energy Functionals for Image Feature Extraction

Ears are an emergent biometric accruing application advantages including no requirement for subject contact and acquisition without demand. To recognize a subject's ear, we aim to extract a characteristic vector from a human ear image that may subsequently be used to identify or confirm the identity of the owner. Towards this end, a novel force field transformation and potential well extraction technique has been developed which leads to a compact characteristic vector offering immunity to initialization, rotation, scale, and noise. The image is transformed by considering the image to consist of an array of Gaussian attractors, which act as the source of a force field. The directional properties of the force field are exploited to automatically locate a small number of potential energy wells, which form the basis of the characteristic vector. We show how this is extracted for a selection of ears, and demonstrate its advantages. As such, we report a new technique in an exciting new biometric.