A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis

Abiodun Adeyinka Oluwabusayo; Adeyemo Adesesan Barnabas

doi:doi:10.11648/j.ajnna.20200602.13

| Peer-Reviewed

A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis

Abiodun Adeyinka Oluwabusayo, Adeyemo Adesesan Barnabas

Published in American Journal of Neural Networks and Applications (Volume 6, Issue 2)

Received: 4 November 2020 Accepted: 2 December 2020 Published: 16 December 2020

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Handwriting is an integral part of our life that can predict who we are because the style of writing is unique for every person. Handwriting is also a key element in document examination as it leaves a forensic document examiner with the task of determining who the writer of a particular document is and this is achieved through the likelihood ratio (L_R) paradigm. Inability to model an individual’s handwriting over time has made estimating a full likelihood ratio for comparative handwriting analysis impossible thereby employing nuisance parameters and subjectivity in computation of L_R that is not full. This research employed back propagation neural network (BPNN) to model the writing pattern of individuals with input layer as the features of handwriting characters, two hidden layers of three neurons each, activation function sigmoid (s) and an output handwriting. With the help of handwriting model for individual writers, little or no assumptions and no nuisance parameters were employed in achieving full likelihood ratio for comparative handwriting analysis in forensic science. From the research carried out, it can be concluded that modeling an individual’s handwriting is a crucial factor in achieving a full likelihood ratio, little/or no inconclusiveness in result reporting and a less degree of disagreements for handwriting identification in a forensic environment.

Published in	American Journal of Neural Networks and Applications (Volume 6, Issue 2)
DOI	10.11648/j.ajnna.20200602.13
Page(s)	29-35
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2020. Published by Science Publishing Group

Keywords

L_R, BPNN, Handwriting, Nuisance Parameter, Forensic Handwriting, Document Examination

References

[1]	C. Champod, I. W. Evett, B. Kuchler, Earmarks as evidence: a critical review, J. Forensic Sci. 46 (2001) 1275–1284.
[2]	C. Neumann, C. Champod, R. Puch-Solis, N. Egli, A. Anthonioz, A. Bromage-Griffiths, Computation of likelihood ratios in fingerprint identification for configurations of any number of minutiae, J. Forensic Sci. 52 (2007) 54–64.
[3]	E. Enzinger (2016). Likelihood ratio calculation in acoustic-phonetic forensic voice comparison: Comparison of three statistical modelling approaches. Proceedings of the Interspeech 2016, 535-539.
[4]	Ruthmara Corzo, Tricia Hoffman, Peter Weis, Javier Franco-Pedroso, Daniel Ramos, Jose Almirall (2018)’The use of LA-ICP-MS databases to calculate likelihood ratios for the forensic analysis of glass evidence’, qq Talanta, Volume 186, Pages 655-661, ISSN 0039-9140.
[5]	Cedric Neumann, Christopher P. Saunders, Commentary on: Alberink I, de Jongh A, Rodriguez C. (2015) Fingermark evidence evaluation based on automated fingerprint identification system matching scores: the effect of different types of conditioning on likelihood ratios. J Forensic Sci 2014; 59 (1): 70–81., Journal of Forensic Sciences, 10.1111/1556-4029.12634, 60, 1, (252-256).
[6]	R. Marquis, S. Bozza, M. Schmittbuhl, F. Taroni, Handwriting evidence evaluation based on the shape of characters: application of multivariate likelihood ratios, J. Forensic Sci. 56 (2011) S238–S242.
[7]	Hepler AB, Saunders CP, Davis LJ, Buscaglia J (2012) Score-based likelihood ratios for handwriting evidence. Forensic Sci Int 219: 129-40.
[8]	Abiodun A. O, Adeyemo A. B (2019) An Exhaustive Mapping Model for Modified Likelihood Ratio for Handwriting Recognition in Forensic Science. J Forensic Sci Criminol 7 (3): 301 ISSN: 2348-9804.
[9]	Alberink I, de Jongh A, Rodriguez C (2013) Fingermark evidence evaluation based on automated fingerprint identification system matching scores: the effect of different types of conditioning on likelihood ratios. J Forensic Sci 59: 70-81.
[10]	Cook R, Evett IW, Jackson G, Jones PJ, Lambert JA (1998) A method for case assessment and interpretation. Sci Just 38: 151-6.
[11]	Royall RM (1997) Statistical Evidence: A Likelihood Paradigm, Chapman & Hall, London.
[12]	Martire K. A., Kemp R. I., Sayle M., & Newell B. R. (2014). On the interpretation of likelihood ratios in forensic science evidence : Presentation formats and the weak evidence effect. Forensic Science International, 240, 61–68. https://doi.org/10.1016/j.forsciint.2014.04.005.
[13]	Marquis R., Bozza S., Schmittbuhl M., Taroni F., (2011) Handwriting evidence evaluation based On the shape of characters: Application of multivariate likelihood ratios, Journal of Forensic Science 56, S238-S242.
[14]	Srihari, S. N., Cha, S., Arora, H., and Lee, S. (2002). Individuality of Handwriting. Journa of Forensic Science, 47 (4), 1–17.
[15]	Aitken G. G. and Taroni F. (2004). Statistics and the Evaluation of Evidence for Forensic Scientists: 2nd edition. John Wiley and Sons.
[16]	Bozza S., Taroni F., Marquis M., Schmittbuhi, (2008) 'Probabilistic evaluation of handwriting evidence: likelihood ratio for authorship' J. R. Stat. Soc. Ser. C: Appl. Stat. 57 329–341.
[17]	Srihari S. N, Beals M. J, Bandi K. Shah V. (2005) A statistical model for writer verification, In: Proceedings of the Eighth International Conference on Document Analysis and Recognition, IEEE Computer Society, pp. 1105-1109.
[18]	Davis, L. J., Saunders, C. P., Hepler, A., and Buscaglia, J. (2012). Using subsampling to estimate the strength of handwriting evidence via score-based likelihood ratios. Forensic Science International, 216 (1–3), 146–157. https://doi.org/10.1016/j.forsciint.2011.09.013.
[19]	Taroni, F., Marquis, R., Schmittbuhl, M., Biedermann, A., Thiéry, A., and Bozza, S. (2012). The use of the likelihood ratio for evaluative and investigative purposes in comparative forensic handwriting examination. Forensic Science International, 214 (1–3), 189–194. https://doi.org/10.1016/j.forsciint.2011.08.007.
[20]	Chen X., Champod, C., Yang, X., Shi, S., Luo, Y., Wang, N. (2018). Assessment of signature handwriting evidence via score-based likelihood ratio based on comparative measurement of relevant dynamic features. Forensic Science International, 282, 101–110. https://doi.org/10.1016/j.forsciint.2017.11.022.
[21]	Ommen D. M., Saunders, C. P., & Neumann, C. (2016). Science and Justice An argument against presenting interval quantifications as a surrogate for the value of evidence. Science & Justice, 56 (5), 383–387. https://doi.org/10.1016/j.scijus.2016.07.001.
[22]	Dawid A. P. (2017). Science and Justice Forensic likelihood ratio: Statistical problems and pitfalls. Science & Justice, 5 7 (1), 73–75. https://doi.org/10.1016/j.scijus.2016.09.002.
[23]	B. S Everitt. The Cambridge Dictionary of Statistics. 3^rd Ed. Cambridge University Press. Cambridge, UK 2006.

Cite This Article

Plain Text BibTeX RIS

APA Style

Abiodun Adeyinka Oluwabusayo, Adeyemo Adesesan Barnabas. (2020). A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. American Journal of Neural Networks and Applications, 6(2), 29-35. https://doi.org/10.11648/j.ajnna.20200602.13

Copy | Download

ACS Style

Abiodun Adeyinka Oluwabusayo; Adeyemo Adesesan Barnabas. A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. Am. J. Neural Netw. Appl. 2020, 6(2), 29-35. doi: 10.11648/j.ajnna.20200602.13

Copy | Download

AMA Style

Abiodun Adeyinka Oluwabusayo, Adeyemo Adesesan Barnabas. A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. Am J Neural Netw Appl. 2020;6(2):29-35. doi: 10.11648/j.ajnna.20200602.13

Copy | Download

@article{10.11648/j.ajnna.20200602.13,
  author = {Abiodun Adeyinka Oluwabusayo and Adeyemo Adesesan Barnabas},
  title = {A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis},
  journal = {American Journal of Neural Networks and Applications},
  volume = {6},
  number = {2},
  pages = {29-35},
  doi = {10.11648/j.ajnna.20200602.13},
  url = {https://doi.org/10.11648/j.ajnna.20200602.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20200602.13},
  abstract = {Handwriting is an integral part of our life that can predict who we are because the style of writing is unique for every person. Handwriting is also a key element in document examination as it leaves a forensic document examiner with the task of determining who the writer of a particular document is and this is achieved through the likelihood ratio (LR) paradigm. Inability to model an individual’s handwriting over time has made estimating a full likelihood ratio for comparative handwriting analysis impossible thereby employing nuisance parameters and subjectivity in computation of LR that is not full. This research employed back propagation neural network (BPNN) to model the writing pattern of individuals with input layer as the features of handwriting characters, two hidden layers of three neurons each, activation function sigmoid (s) and an output handwriting. With the help of handwriting model for individual writers, little or no assumptions and no nuisance parameters were employed in achieving full likelihood ratio for comparative handwriting analysis in forensic science. From the research carried out, it can be concluded that modeling an individual’s handwriting is a crucial factor in achieving a full likelihood ratio, little/or no inconclusiveness in result reporting and a less degree of disagreements for handwriting identification in a forensic environment.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis
AU  - Abiodun Adeyinka Oluwabusayo
AU  - Adeyemo Adesesan Barnabas
Y1  - 2020/12/16
PY  - 2020
N1  - https://doi.org/10.11648/j.ajnna.20200602.13
DO  - 10.11648/j.ajnna.20200602.13
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 29
EP  - 35
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20200602.13
AB  - Handwriting is an integral part of our life that can predict who we are because the style of writing is unique for every person. Handwriting is also a key element in document examination as it leaves a forensic document examiner with the task of determining who the writer of a particular document is and this is achieved through the likelihood ratio (LR) paradigm. Inability to model an individual’s handwriting over time has made estimating a full likelihood ratio for comparative handwriting analysis impossible thereby employing nuisance parameters and subjectivity in computation of LR that is not full. This research employed back propagation neural network (BPNN) to model the writing pattern of individuals with input layer as the features of handwriting characters, two hidden layers of three neurons each, activation function sigmoid (s) and an output handwriting. With the help of handwriting model for individual writers, little or no assumptions and no nuisance parameters were employed in achieving full likelihood ratio for comparative handwriting analysis in forensic science. From the research carried out, it can be concluded that modeling an individual’s handwriting is a crucial factor in achieving a full likelihood ratio, little/or no inconclusiveness in result reporting and a less degree of disagreements for handwriting identification in a forensic environment.
VL  - 6
IS  - 2
ER  -

Copy | Download

Author Information

Abiodun Adeyinka Oluwabusayo

Department of Computer Science & Information Technology, Bowen University, Iwo, Nigeria
Adeyemo Adesesan Barnabas

Department of Computer Science, University of Ibadan, Ibadan, Nigeria

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Abiodun Adeyinka Oluwabusayo, Adeyemo Adesesan Barnabas. (2020). A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. American Journal of Neural Networks and Applications, 6(2), 29-35. https://doi.org/10.11648/j.ajnna.20200602.13

Copy | Download

ACS Style

Abiodun Adeyinka Oluwabusayo; Adeyemo Adesesan Barnabas. A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. Am. J. Neural Netw. Appl. 2020, 6(2), 29-35. doi: 10.11648/j.ajnna.20200602.13

Copy | Download

AMA Style

Abiodun Adeyinka Oluwabusayo, Adeyemo Adesesan Barnabas. A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis. Am J Neural Netw Appl. 2020;6(2):29-35. doi: 10.11648/j.ajnna.20200602.13

Copy | Download

@article{10.11648/j.ajnna.20200602.13,
  author = {Abiodun Adeyinka Oluwabusayo and Adeyemo Adesesan Barnabas},
  title = {A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis},
  journal = {American Journal of Neural Networks and Applications},
  volume = {6},
  number = {2},
  pages = {29-35},
  doi = {10.11648/j.ajnna.20200602.13},
  url = {https://doi.org/10.11648/j.ajnna.20200602.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20200602.13},
  abstract = {Handwriting is an integral part of our life that can predict who we are because the style of writing is unique for every person. Handwriting is also a key element in document examination as it leaves a forensic document examiner with the task of determining who the writer of a particular document is and this is achieved through the likelihood ratio (LR) paradigm. Inability to model an individual’s handwriting over time has made estimating a full likelihood ratio for comparative handwriting analysis impossible thereby employing nuisance parameters and subjectivity in computation of LR that is not full. This research employed back propagation neural network (BPNN) to model the writing pattern of individuals with input layer as the features of handwriting characters, two hidden layers of three neurons each, activation function sigmoid (s) and an output handwriting. With the help of handwriting model for individual writers, little or no assumptions and no nuisance parameters were employed in achieving full likelihood ratio for comparative handwriting analysis in forensic science. From the research carried out, it can be concluded that modeling an individual’s handwriting is a crucial factor in achieving a full likelihood ratio, little/or no inconclusiveness in result reporting and a less degree of disagreements for handwriting identification in a forensic environment.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - A Neural Network Approach to Writer’s Model for Full Likelihood Ratio in Handwriting Analysis
AU  - Abiodun Adeyinka Oluwabusayo
AU  - Adeyemo Adesesan Barnabas
Y1  - 2020/12/16
PY  - 2020
N1  - https://doi.org/10.11648/j.ajnna.20200602.13
DO  - 10.11648/j.ajnna.20200602.13
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 29
EP  - 35
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20200602.13
AB  - Handwriting is an integral part of our life that can predict who we are because the style of writing is unique for every person. Handwriting is also a key element in document examination as it leaves a forensic document examiner with the task of determining who the writer of a particular document is and this is achieved through the likelihood ratio (LR) paradigm. Inability to model an individual’s handwriting over time has made estimating a full likelihood ratio for comparative handwriting analysis impossible thereby employing nuisance parameters and subjectivity in computation of LR that is not full. This research employed back propagation neural network (BPNN) to model the writing pattern of individuals with input layer as the features of handwriting characters, two hidden layers of three neurons each, activation function sigmoid (s) and an output handwriting. With the help of handwriting model for individual writers, little or no assumptions and no nuisance parameters were employed in achieving full likelihood ratio for comparative handwriting analysis in forensic science. From the research carried out, it can be concluded that modeling an individual’s handwriting is a crucial factor in achieving a full likelihood ratio, little/or no inconclusiveness in result reporting and a less degree of disagreements for handwriting identification in a forensic environment.
VL  - 6
IS  - 2
ER  -

Copy | Download