Force Field Feature Extraction for Ear Biometrics

Abstract

The overall objective in defining feature space is to reduce the dimensionality of the original pattern space, whilst maintaining discriminatory power for classification. To meet this objective in the context of ear biometrics a new force field transformation treats the image as an array of mutually attracting particles that act as the source of a Gaussian force field. Underlying the force field there is a scalar potential energy field, which in the case of an ear takes the form of a smooth surface that resembles a small mountain with a number of peaks joined by ridges. The peaks correspond to potential energy wells and to extend the analogy the ridges correspond to potential energy channels. Since the transform also turns out to be invertible, and since the surface is otherwise smooth, information theory suggests that much of the information is transferred to these features, thus confirming their efficacy. We previously described how field line feature extraction, using an algorithm similar to gradient descent, exploits the directional properties of the force field to automatically locate these channels and wells, which then form the basis of characteristic ear features. We now show how an analysis of the mechanism of this algorithmic approach leads to a closed analytical description based on the divergence of force direction, which reveals that channels and wells are really manifestations of the same phenomenon. We further show that this new operator, with its own distinct advantages, has a striking similarity to the Marr-Hildreth operator, but with the important difference that it is non-linear. As well as addressing faster implementation, invertibility, and brightness sensitivity, the technique is also validated by performing recognition on a database of ears selected from the XM2VTS face database, and by comparing the results with the more established technique of Principal Components Analysis. This confirms not only that ears do indeed

State of the art and perspectives on traditional and emerging biometrics: A survey

“…Ear biometric features include the outer helix, scapha, antihelix, lobe, crus antihelicis, tragus, antitragus, and concha. 100 While the potential for using the human ear for identification has been highlighted since the 1890s by Bertillon, 101 it is only in the 1990s that the first attempt to build an ear biometric recognition system was made, specifically by Burge and Burger. 102 Since then, more work has been done in laying the foundation for this new biometric.…”

Haar-like rectangular features for biometric recognition

“…The results of the proposed system for the ear are compared against the very recent publication of [11] in which the localized orientation information and local graylevel phase information are used in complex Gabor filters. Besides the best results reported in [11], the Force Field Transform (FFT) method of [7] has also been included in the comparisons. The results of the FFT method on the employed ear databases are taken from [11].…”

“…Several features based classifiers are also reported in the literature for the chosen biometrics. For example for ear images a Force Filed Transform based classifier in [7], a structural feature based method in [13], and a Gabor filter based method in [11] can be mentioned. Among the feature based methods for hand vein pattern in [16] the end points and the crossing points of the veins, in [17] the Scale Invariant Feature Transform (SIFT) features, in [5] Non-negative Matrix Factorization based features and in [3] Line Edge Mapping based features have been used.…”

Unsupervised 3d Segmentation of Hippocampus in Brain MR Images

“…The Field force experienced by a voxel at position r i due to its neighbourhood W is given by the force field transformation (Hurley et al, 2005) as…”