Journal of Pattern Recognition Research

Biometric traits along with various evidences left by the offender at the place of crime found useful in crime investigation. In this paper a rotation and intensity invariant approach of automatic shoeprint verification have been discussed. Directional features of a shoeprint have been extracted using Radon transform. Also, rotation of a shoeprint image is estimated using the directional features. Experiments have been carried out on locally generated database. Performance of the algorithms have been evaluated in terms of Correct Recognition Rate computed using best Match Score for rank ‘1’ and cumulative match score for the first four matches. The proposed algorithm has been compared with present related art. It is found that the proposed algorithm performs better for intensity variations. Also, the computations required are minimized significantly. Experimentation has also been carried out by perturbing shoeprint images with Gaussian white noise, salt and pepper noise to evaluate the robustness of the proposed technique.