Authors : Sashwath Kishore K.; Mohameed Faaiq Dhanish; Dr. Revathi A.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/4u47fdru

DOI : https://doi.org/10.38124/ijisrt/26apr2218

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Bloodstain pattern analysis (BPA) is a critical forensic science tool for reconstructing crime scene events and understanding the dynamics of violent incidents. Traditionally conducted through manual analysis by trained experts, this process is time-consuming, subjective, and prone to contextual bias. This paper presents a comprehensive deep learning frame-work integrating convolutional neural networks (CNN) for auto-mated detection, classification, and impact angle determination of bloodstain patterns.

Keywords : Bloodstain Pattern Analysis, Deep Learning, Con-Volutional Neural Networks, Computer Vision, Forensic Science, Crime Scene Reconstruction, Impact Angle Analysis, Pattern Clas-Sification, Machine Learning, Edge AI.

References :

1. “Classification of bloodstain spatter patterns with convolutional neural networks,” in Proc. IEEE Int. Conf. Image Vision Computing New Zealand (IVCNZ), 2024. [Online]. Available: https://ieeexplore.ieee.org/ document/10794486/
2. “A fast and compact hybrid CNN for hyperspectral imaging-based blood-stain classification,” in Proc. IEEE Congress Evolutionary Computation (CEC), 2022. [Online]. Available: https://ieeexplore.ieee.org/document/ 9870277/
3. “Bloodstain classification in forensic analysis using optimized 3D CNN,” in Proc. IEEE Conf., 2023. [Online]. Available: https://ieeexplore.ieee. org/document/10534494/
4. “Integrating AI and computer vision for ballistic and bloodstain analysis in 3D digital forensics,” in Proc. IEEE Conf., 2024. [Online]. Available: https://ieeexplore.ieee.org/document/10796512/
5. “Bloodstain identification based on visible/near-infrared hyperspectral imaging with convolutional neural network,” IEEE J. Mag., 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9844736/
6. “From images to detection: Machine learning for blood pattern classi-fication,” Forensic Sci. Int., vol. 375, 2025. [Online]. Available: https: //www.sciencedirect.com/science/article/abs/pii/S0379073825001963
7. “A first step towards a machine learning-based framework for bloodstain classification in forensic science,” Forensic Sci. Int., vol. 365, pp. 111–125, 2024. [Online]. Available: https://www.sciencedirect.com/science/ article/abs/pii/S0379073824003608
8. “An automated method for the generation of bloodstain pattern metrics from images of blood spatter patterns,” Forensic Sci. Int., vol. 363, pp. 111–120, 2024. [Online]. Available: https://www.sciencedirect.com/ science/article/abs/pii/S0379073824002810
9. “Automatic classification of bloodstains with deep learning methods,” KI – Ku¨nstliche Intelligenz, vol. 36, pp. 45–62, 2022. [Online]. Available: https://link.springer.com/article/10.1007/s13218-022-00760-y
10. “Unsupervised machine learning for the detection and interpretation of key features in drip patterns,” Forensic Sci. Int., vol. 361, pp. 111–130, 2025. [Online]. Available: https://www.sciencedirect.com/science/ article/abs/pii/S0379073825003135
11. “Bloodstain in forensics: From visual inspections to AI-assisted pat-tern analysis and age estimation,” History Sci. Technol., vol. 15, no. 1, 2025. [Online]. Available: https://www.hstjournal.com/index.php/hst/ article/view/688
12. “Enhancing bloodstain analysis through AI-based segmentation: Lever-aging segment anything model for crime scene investigation,” arXiv, 2024. [Online]. Available: https://ar5iv.labs.arxiv.org/html/2308.13979
13. “Analysis of passive bloodstain morphology across surface textures and drop heights using deep learning,” Forensic Sci. Int., vol. 363, pp. 111–145, 2026. [Online]. Available: https://www.sciencedirect.com/science/ article/abs/pii/S0379073826000770
14. “A comparison of deep learning methods for multi-class classification of bloodstain patterns,” in Springer Nature, Computational Intelligence, 2024, ch. 21. [Online]. Available: https://link.springer.com/chapter/10. 1007/978-981-96-4596-121
15. “An efficient image classification and segmentation method for crime investigation applications,” Multimedia Tools Appl., Springer, 2024. [Online]. Available: https://link.springer.com/article/10.1007/ s11042-024-19773-w