Sexing white 2D footprints using convolutional neural networks

Authors: Budka, M., Bennett, M.R., Reynolds, S.C., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PLoS ONE

Volume: 16

Issue: 8 August

eISSN: 1932-6203

DOI: 10.1371/journal.pone.0255630

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N = 196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N = 2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N = 267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

Source: Scopus

Sexing white 2D footprints using convolutional neural networks.

Authors: Budka, M., Bennett, M.R., Reynolds, S.C., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PLoS One

Volume: 16

Issue: 8

Pages: e0255630

eISSN: 1932-6203

DOI: 10.1371/journal.pone.0255630

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N = 196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N = 2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N = 267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

Source: PubMed

Sexing white 2D footprints using convolutional neural networks

Authors: Budka, M., Bennett, M.R., Reynolds, S.C., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PLOS ONE

Volume: 16

Issue: 8

ISSN: 1932-6203

DOI: 10.1371/journal.pone.0255630

https://eprints.bournemouth.ac.uk/37622/

Source: Web of Science (Lite)

Sexing Caucasian 2D footprints using convolutional neural networks

Authors: Budka, M., Bennett, M., Reynolds, S., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PLoS One

Publisher: Public Library of Science (PLoS)

ISSN: 1932-6203

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N=196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N=2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N=267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

Source: Manual

Sexing Caucasian 2D footprints using convolutional neural networks.

Authors: Budka, M., Bennet, M.R., Reynolds, S., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: CoRR

Volume: abs/2108.01554

https://eprints.bournemouth.ac.uk/37622/

Source: DBLP

Sexing white 2D footprints using convolutional neural networks.

Authors: Budka, M., Bennett, M.R., Reynolds, S.C., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PloS one

Volume: 16

Issue: 8

Pages: e0255630

eISSN: 1932-6203

ISSN: 1932-6203

DOI: 10.1371/journal.pone.0255630

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N = 196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N = 2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N = 267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

Source: Europe PubMed Central

Sexing Caucasian 2D footprints using convolutional neural networks

Authors: Budka, M., Bennet, M.R., Reynolds, S., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N=196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N=2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N=267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

http://dx.doi.org/10.1371/journal.pone.0255630

Source: arXiv

Sexing white 2D footprints using convolutional neural networks

Authors: Budka, M., Bennett, M.R., Reynolds, S.C., Barefoot, S., Reel, S., Reidy, S. and Walker, J.

Journal: PLoS ONE

Volume: 16

Issue: 8

Publisher: Public Library of Science (PLoS)

ISSN: 1932-6203

Abstract:

Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N = 196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N = 2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N = 267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.

https://eprints.bournemouth.ac.uk/37622/

http://dx.doi.org/10.1371/journal.pone.0255630

Source: BURO EPrints