Skip to main content

Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification.

Budka, M., Ashraf, A.W.U., Neville, S., Mackrill, A. and Bennett, M. R., 2021. Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification. arXiv (2102.05090 [cs.CV]).

Full text available as:

[img]
Preview
PDF (arXiv preprint)
2102.05090v1.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial.

19MB

Official URL: http://arxiv.org/abs/2102.05090

Abstract

In recent years deep neural networks have become the workhorse of computer vision. In this paper, we employ a deep learning approach to classify footwear impression's features known as \emph{descriptors} for forensic use cases. Within this process, we develop and evaluate an effective technique for feeding downsampled greyscale impressions to a neural network pre-trained on data from a different domain. Our approach relies on learnable preprocessing layer paired with multiple interpolation methods used in parallel. We empirically show that this technique outperforms using a single type of interpolated image without learnable preprocessing, and can help to avoid the computational penalty related to using high resolution inputs, by making more efficient use of the low resolution inputs. We also investigate the effect of preserving the aspect ratio of the inputs, which leads to considerable boost in accuracy without increasing the computational budget with respect to squished rectangular images. Finally, we formulate a set of best practices for transfer learning with greyscale inputs, potentially widely applicable in computer vision tasks ranging from footwear impression classification to medical imaging.

Item Type:Article
ISSN:1524-0703
Uncontrolled Keywords:cs.CV ; cs.CV
Group:Faculty of Science & Technology
ID Code:35635
Deposited By: Symplectic RT2
Deposited On:14 Jun 2021 13:59
Last Modified:14 Mar 2022 14:28

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -