In this paper, we present a method for automatically classifying/recognizing the shoeprint images based on the outsole pattern. Shoeprints are distinctive patterns often found at crime scenes that can provide valuable forensic evidence. Directionality is the most obvious feature in these shoeprints. For extracting features corresponding to the directionality, co-occurrence matrices, Fourier transform, and a directional matrix are applied to the shoeprint image. With the stage of principal component transform, the method is invariant to rotation and translation variance. Experimental results demonstrate the performance of the method.
|Title of host publication||PROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6|
|Number of pages||6|
|State||Published - 2009|
|Event||2009 International Conference on Machine Learning and Cybernetics - Baoding, China|
Duration: 12 Jul 2009 → 15 Jul 2009
|Conference||2009 International Conference on Machine Learning and Cybernetics|
|Period||12/07/09 → 15/07/09|
- Forensic science; Shoeprint; Fourier transforms; Co-occurrence matrix; Principal component transform
Jing, M-Q., Wei, J. H., & Chen, L-H. (2009). A NOVEL METHOD FOR SHOEPRINTS RECOGNITION AND CLASSIFICATION. In PROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6 (pp. 2846-2851). IEEE.