Automated Firearm and Ammunition Identification: The Role of Artificial Intelligence in Forensic Ballistics

Background/Objectives: This paper focusses on the use of artificial intelligence (AI) in automated firearm and ammunition identification. It concentrates on firing pin impressions on fired cartridge cases and secondary rifling land impressions on fired bullets, since these traces represent two different problems in forensic ballistic comparison. The main question was whether machine learning and deep learning methods can support the comparison process while the final assessment remains in the hands of the firearms examiner. Methods: This study combines a critical methodological analysis of AI-based firearm identification with applied experimental results. A convolutional neural network (CNN) was used for firing pin mark classification, the reliability of which was assessed using output neuron parameters A1, A1/A2, and A1−A2. For bullet marks, CNN-based semantic binarization was applied to secondary rifling land impressions, followed by random forest classification of the binarized image pairs. Data augmentation was used to address the limited number of original training objects in this study. Results: Considering the three highest CNN output signals increased the overall firing pin classification accuracy from 82.6% to 92.8%, while the accuracy for unknown-class marks increased from 60.8% to 79.1%. CNN-based binarization of bullet marks achieved accuracy = 0.88 ± 0.05, recall = 0.76 ± 0.06, precision = 0.83 ± 0.06, F1 = 0.79 ± 0.05, and MCC = 0.71 ± 0.06. The random forest classification of binarized bullet mark pairs achieved an accuracy of approximately 84–86%. Conclusions: The findings indicate that AI can improve speed, consistency, candidate selection, image preprocessing, and reliability assessment in forensic ballistics. However, AI outputs remain dependent on dataset quality, firearm and ammunition variability, unknown class recognition, and external validation. The most reliable model is a hybrid human–AI workflow in which the algorithm supports the firearms examiner but does not replace expert judgement.