Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification.
Authors: Budka, M., Wahid-Ul-Ashraf, A., Neville, S., Mackrill, A. and Bennett, M.
Journal: CoRR
Volume: abs/2102.05090
https://eprints.bournemouth.ac.uk/35635/
Source: DBLP
Preferred by: Marcin Budka
Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification
Authors: Budka, M., Ashraf, A.W.U., Neville, S., Mackrill, A. and Bennett, M.
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.
https://eprints.bournemouth.ac.uk/35635/
Source: arXiv
Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification
Authors: Budka, M., Ashraf, A.W.U., Neville, S., Mackrill, A. and Bennett, M.R.
Journal: arXiv
Issue: 2102.05090 [cs.CV]
ISSN: 1524-0703
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.
https://eprints.bournemouth.ac.uk/35635/
http://arxiv.org/abs/2102.05090
Source: BURO EPrints