Using subsampling to estimate the strength of handwriting evidence via score-based likelihood ratios

Davis, Linda; Saunders, Christopher P.; Hepler, Amanda B.; Buscaglia, JoAnn

doi:10.1016/j.forsciint.2011.09.013

Cited by 32 publications

(30 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ramos [14] studied the effect of using suspect-independent within-source scores instead of suspect-anchored approach on the resultant LRs in the context of speaker recognition. [77] describes the effect(s) of different calibrations data used to construct the denominator distribution in the context of handwriting recognition. We compute two functions from score to LLR using the suspect-anchored and suspect-independent sets of calibration scores.…”

Section: Comparing the Resultant Lrsmentioning

confidence: 99%

“…A detailed description of this approach to LR computation is presented by Meuwly [57] in the context of forensic speaker identification and subsequently adapted by [23,54,77] for other biometric modalities.…”

Section: Kernel Density Estimation (Kde)mentioning

confidence: 99%

“…Certain specific solutions have appeared as how to increase the number of the within-source and the between-source scores to estimate the distribution of scores under the prosecution and defense hypothesis [14,77]. A general solution to this problem is to compute the within-source scores by considering pairs of images from multiple potential suspects in the potential population database.…”

Section: Suspect-independent Approachmentioning

confidence: 99%

“…Certain specific solutions have been proposed as how to increase the number of the within-source scores when following the suspect-specific approach [14,77]. A general solution is to construct the within-source scores set by combining the suspect-specific within-source scores sets of multiple persons from the potential population database.…”

Section: Suspect-independent (Generic) Training Datamentioning

confidence: 99%

“…Ramos [14] proposed a strategy which is based on the adaptation of the suspect-independent within-source scores distribution to the suspect-specific scores via Maximum A Posteriori (MAP) estimation. Similarly, in forensic handwriting recognition, Davis [77] generated a large set of simulated writing specimens from a small set of suspect specimens to form a data set for computation of the suspectspecific within-source scores. These specific approaches do not generalize in most cases and usually a suspect-independent approach is considered as a last 4.3 Biometric evidence evaluation: an empirical assessment of the effect of different training data 83 resort to compute a reliable LR for the given pair of biometric specimens [88].…”

Section: Motivationmentioning

confidence: 99%

See 4 more Smart Citations

Biometric score calibration for forensic face recognition

Ali¹

View full text Add to dashboard Cite

Section: Comparing the Resultant Lrsmentioning

confidence: 99%

Section: Kernel Density Estimation (Kde)mentioning

confidence: 99%

Section: Suspect-independent Approachmentioning

confidence: 99%

Section: Suspect-independent (Generic) Training Datamentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 3 more Smart Citations

Biometric score calibration for forensic face recognition

Ali¹

View full text Add to dashboard Cite

References

2020

Statistics and the Evaluation of Evidence for Forensic Scientists 3e

View full text Add to dashboard Cite

Ink source prediction and assessment based on direct analysis in real‐time mass spectrometry via the likelihood ratio

Zhang

Yang

Tang

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

Ink classification is the ability to distinguish unknown inks into different groups, and ink source prediction is the ability to predict the manufacturer or model of an unknown ink. These are regular tasks in forensic analysis. The latter is more challenging than the former, as ink source prediction has expanded beyond ink classification. In this work, we reported on an approach to predict the source of black inks based on direct analysis in real time mass spectrometry and assess the strength of black ink source prediction conclusion via the likelihood ratio, using a dataset that included 39 inks from three manufacturers with a high market share. Most of these inks contain similar or identical chemical components. Dimensionality reduction based on the principal component analysis and unified manifold approximation and projection algorithms was implemented, and subsequently, the distribution plots illustrated the variations between and within the inks. Unified manifold approximation and projection showed significant priority in avoiding overcrowding of cluster representation versus principal component analysis, with results as high as 99.83% for the prediction of the ink source using 41,432 spectra data (70% data for training and 30% data for testing) after dimensionality reduction. A likelihood ratio was used to evaluate the strength of ink evidence, and the pool‐adjacent‐violators algorithm and logistic algorithms were used to calibrate the likelihood ratio. The results showed that the pool‐adjacent‐violators algorithm and logistic algorithms both had an excellent equal error rate of 0.004 but slightly different results in the rates of misleading evidence in favor of the prosecutor's hypothesis, rates of misleading evidence in favor of the defense's hypothesis, log likelihood ratio costs after calibration ( Cllrcal), and minimum log likelihood ratio costs ( Cllrmin). A blind test validated the robustness of the methods.

show abstract

Using subsampling to estimate the strength of handwriting evidence via score-based likelihood ratios

Cited by 32 publications

References 24 publications

Biometric score calibration for forensic face recognition

Biometric score calibration for forensic face recognition

References

Ink source prediction and assessment based on direct analysis in real‐time mass spectrometry via the likelihood ratio

Contact Info

Product

Resources

About