*Result*: A preliminary investigation into the classification of wipe and swipe bloodstain patterns between human and artificial intelligence.
Original Publication: [Chicago, Ill.] : Callaghan and Co., 1956-
Oxygen. Former state trooper wrongfully convicted twice of killing wife, children wins settlement. 2022. Available from: https://www.oxygen.com/crime‐news/david‐camm‐settles‐suit‐wrongful‐murder‐convictions‐wife‐kids. Accessed 22 July 2025.
Taylor MC, Laber TL, Kish PE, Owens G, Osborne NK. The reliability of pattern classification in bloodstain pattern analysis, part 1: bloodstain patterns on rigid non‐absorbent surfaces. Journal of Forensic Sciences. 2016;61(4):922–927. https://doi.org/10.1111/1556‐4029.13091.
Yuen SK, Taylor MC, Owens G, Elliot DA. The reliability of swipe/wipe classification and directionality determination methods in bloodstain pattern analysis. Journal of Forensic Sciences. 2017;62(4):1037–1042. https://doi.org/10.1111/1556‐4029.13298.
National Institute of Standards and Technology. OSAC 2022‐S‐0030: Standard for methodology in bloodstain pattern analysis (draft). 2022. Available from: https://www.nist.gov/system/files/documents/2022/02/28/OSAC%202022‐S‐0030%20Standard%20for%20Methodology%20in%20Bloodstain%20Pattern%20Analysis.OPEN%20COMMENT%20VERSION.pdf. Accessed 29 Oct 2025.
Wonder AY. Bloodstain patterns: identification, interpretation and application. London, UK: Academic Press; 2015.
Bevel T, Gardner R. Bloodstain pattern analysis. 2nd ed. Boca Raton, FL: CRC Press; 2001.
Jung H, Jo YS, Ahn YJ, Jeong JP, Lim SK. A first step towards a machine learning‐based framework for bloodstain classification in forensic science. Forensic Science International. 2024;365(1):111703. https://doi.org/10.1016/j.forsciint.2024.112278.
Gardner RM. Directionality in swipe patterns. J Forensic Identif. 2002;52(5):579–593.
Rickeard BW. An investigation into bloodstain pattern analysis: the reliability of swipe/wipe and directionality determination approaches [thesis]. Windsor, ON, Canada: University of Windsor; 2018. Available from: https://www.semanticscholar.org/paper/An‐Investigation‐into‐Bloodstain‐Pattern‐Analysis%3A‐Rickeard/dfb7c82f6833beef74e2d0d9d7b01d506b1a7d27. Accessed 22 Jul 2025.
Microsoft. Azure AI Custom Vision. 2024. Available from: https://azure.microsoft.com/en‐us/products/ai‐services/ai‐custom‐vision. Accessed 22 Jul 2025.
*Further Information*
*Bloodstain pattern types, such as wipes and swipes, are frequently encountered at crime scenes and can offer critical insight into the sequence of events. However, these pattern types can be difficult to reliably distinguish, highlighting the need for modern, objective approaches to classification that reduce the potential for human error. In this study, 50 participants were asked to classify 40 test bloodstain pattern images (20 wipes and 20 swipes). These same images were subsequently classified using Microsoft Azure Custom Vision (MACV), an artificial intelligence (AI) image recognition platform. The MACV model was trained using 5425 bloodstain pattern images, including impact, expirated, cessation cast-off, wipe, and swipe stains, across a range of background colors. At the 50th training iteration, the AI achieved 100% accuracy in classifying both wipe and swipe patterns, outperforming participants who achieved an average accuracy of 52% (47% for wipes and 57% for swipes), marking a 48% improvement in classification performance. The model was further trained to the 80th iteration using rotated images, achieving 98.75% accuracy on the rotated test set.
(© 2025 American Academy of Forensic Sciences.)*