Frequency Map by Structure Tensor in Logarithmic Scale Space and Forensic Fingerprints

Josef Bigun, Anna Mikaelyan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 136-145

Abstract


Increasingly, absolute frequency and orientation maps are needed, e.g. for forensics. We introduce a non-linear scale space via the logarithm of trace of the Structure Tensor. Therein, frequency estimation becomes an orientation estimation problem. We show that this offers significant advantages, including construction of efficient isotropic estimations of dense maps of frequency. In fingerprints, both maps are shown to improve each other in an enhancement scheme via Gabor filtering. We suggest a novel continuous ridge counting method, relying only on dense absolute frequency and orientation maps, without ridge detection, thinning, etc. Furthermore, we present new evidence that frequency maps are useful attributes of minutiae. We verify that the suggested method compares favorably with state of the art using forensic fingerprints as test bed, and test images where the ground truth is known. In evaluations, we use public data sets and published methods only.

Related Material


[pdf]
[bibtex]
@InProceedings{Bigun_2016_CVPR_Workshops,
author = {Bigun, Josef and Mikaelyan, Anna},
title = {Frequency Map by Structure Tensor in Logarithmic Scale Space and Forensic Fingerprints},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}