Combined interpretation of objective firearm evidence comparison algorithms using Bayesian networks

Journal of Forensic Sciences, Journal Year: 2024, Volume and Issue: 69(6), P. 2028 - 2040

Published: Aug. 22, 2024

Abstract Traditionally, firearm and toolmark examiners manually evaluate the similarity of features on two bullets using comparison microscopy. Advances in microscopy have made it possible to collect 3D topographic data, several automated algorithms been introduced for bullet striae these data. In this study, open‐source approaches cross‐correlation, congruent matching profile segments, consecutive striations, a random forest model were evaluated. A statistical characterization was performed four datasets consecutively manufactured firearms provide challenging scenario. Each approach applied all samples pairwise fashion, classification performance compared. Based findings, Bayesian network empirically learned constructed leverage strengths each individual approach, relationship between results, combine them into posterior probability given comparison. The evaluated similarly approaches, results developed classified 99.6% correctly, resultant distributions significantly separated more so than when used isolation.

Language: Английский

---

Fired bullet signature correlation using the finite ridgelet transform (FRIT) and the gray level co-occurrence matrix (GLCM) methods

Forensic Science International, Journal Year: 2021, Volume and Issue: 330, P. 111089 - 111089

Published: Oct. 29, 2021

Language: Английский

---

Examination of the possibility to use Siamese networks for the comparison of firing pin marks

Journal of Forensic Sciences, Journal Year: 2022, Volume and Issue: 67(6), P. 2416 - 2424

Published: Sept. 23, 2022

One of the most discussed issues in forensic firearms identification is subjectivity conclusions. The main part examiners' work to make a microscopic comparison marks on cartridge cases and bullets. In this process, examiners have decide if quantity quality observed characteristics are sufficient for identification. This decision based personal experience an examiner, so with different backgrounds can come conclusions, fact presents problem. Besides, calculation error rate type examination debatable issue. Different mathematical statistical models were proposed, computer-based algorithms developed order avoid determine rates. article investigates possibility use methods machine learning firing pin impressions cases. research, Siamese network model, which included two similar Convolutional Neural Networks, was prepared trained. For training validation database prepared. images discharged from 300 that came regular casework clone used data augmentation. model trained examined using database. metrics, such as accuracy, sensitivity, specificity calculated. results research show building objective system known rate.

Language: Английский

---

Interpol review of forensic firearm examination 2019–2022

Forensic Science International Synergy, Journal Year: 2022, Volume and Issue: 6, P. 100305 - 100305

Published: Dec. 14, 2022

Language: Английский

---

Identification of bullets fired from air guns using machine and deep learning methods

Forensic Science International, Journal Year: 2023, Volume and Issue: 349, P. 111734 - 111734

Published: May 19, 2023

Ballistics (the linkage of bullets and cartridge cases to weapons) is a common type evidence encountered in criminal around the world. The interest lies determining whether two were fired using same firearm. This paper proposes an automated method classify from surface topography Land Engraved Area (LEA) images pellets machine deep learning methods. curvature was removed loess fit features extracted Empirical Mode Decomposition (EMD) followed by various entropy measures. informative identified minimum Redundancy Maximum Relevance (mRMR), finally classification performed Support Vector Machines (SVM), Decision Tree (DT) Random Forest (RF) classifiers. results revealed good predictive performance. In addition, model DenseNet121 used LEA images. provided higher performance than SVM, DT RF Moreover, Grad-CAM technique visualise discriminative regions These suggest that proposed can be expedite projectiles firearms assist ballistic examinations. this work, compared air both rifles high velocity pistol. Air guns collect data because they more accessible other could as proxy, delivering comparable LEAs. methods developed here proof-of-concept are easily expandable bullet case identification any weapon.

Language: Английский

---

Virtual image standard (VIS) for performance evaluation of the congruent matching cells (CMC) algorithms in firearm evidence identifications

Journal of Forensic Sciences, Journal Year: 2022, Volume and Issue: 67(4), P. 1417 - 1430

Published: March 9, 2022

The congruent matching cells (CMC) method was invented at the National Institute of Standards and Technology (NIST) in 2012 for automatic objective firearm evidence identifications estimation weight identifications. Since 2013, five CMC algorithms have been developed NIST. In this paper, virtual image standard (VIS) is proposed through trimming stitching KNM images quantitative performance evaluations different algorithms. evaluation criteria include correlation accuracy (both numbers distribution pattern), efficiency, false positive (FP) error rate, maximum separation known (KM) non-matching (KNM) pairs. VIS composes from images, which can provide a ground truth verifying numbers, patterns, FP errors. By identifying three groups VIS, Convergence algorithm showed superior performances future casework Lastly, success study suggests that could also be used to optimize parameters, develop test new algorithms, evaluate before it put into use examiner's casework.

Language: Английский

---

Generalizable features-based method for breech face comparisons

Published: Sept. 13, 2024

Language: Английский

---

Automated interpretation of comparison scores for firearm toolmarks on cartridge case primers

Forensic Science International, Journal Year: 2023, Volume and Issue: 353, P. 111858 - 111858

Published: Oct. 12, 2023

Language: Английский

---

МЕТОДЫ СТАТИСТИЧЕСКОГО АНАЛИЗА И МАШИННОГО ОБУЧЕНИЯ В СУДЕБНО-БАЛЛИСТИЧЕСКОЙ ЭКСПЕРТИЗЕ

ԴԱՏԱԿԱՆ ՓՈՐՁԱՔՆՆՈՒԹՅԱՆ ԵՎ ՔՐԵԱԳԻՏՈՒԹՅԱՆ ՀԱՅԿԱԿԱՆ ՀԱՆԴԵՍ, Journal Year: 2023, Volume and Issue: unknown, P. 118 - 126

Published: Jan. 1, 2023

В настоящее время в отдельных экспертных исследованиях применяют методы статистического анализа и машинного обучения. Их широкое внедрение экспертную практику осложняется отсутствием у экспертов компетенций области современных методов анализа, к которым можно отнести работе рассмотрены современные методики, основанные на статистическом анализе методах обучения, адаптированные для решения задач судебной баллистики баллистической идентификации. Внедрение таких методик ведет изменению парадигмы формирования категорических выводов. Суть изменений заключается переходе от модели, когда категорические выводы эксперта опираются основном его внутреннее убеждение, где убеждение формируется основе количественной оценки доказываемого факта, которая должна быть предъявлена суду может перепроверена другими независимыми специалистами. Для широкого внедрения математических сравнения схожести следов, предварительно необходимо обеспечить возможность приобретения экспертами «соответствующих» компетенций. С этой целью была разработана дисциплина «Математические судебно-баллистической экспертизе», взята за основу курсов повышения квалификации экспертов-баллистов, имеющих естественно-научное или техническое высшее образование. Ключевые слова: идентификация огнестрельного оружия, компетенции, судебно-баллистическая экспертиза, курсы квалификации.

Language: Русский

---

Creating a Prototype for a Bullet-Resistant Implant: Application in Breast Prosthetics

Human Factors and Mechanical Engineering for Defense and Safety, Journal Year: 2023, Volume and Issue: 7(1)

Published: Dec. 1, 2023

Language: Английский

---