Application of hyperspectral imaging and machine learning methods for the detection of gunshot residue patterns

Advanced image processing algorithms can support the forensic analyst to make tasks like detection, pattern comparison or identification more objective. In the case of the gunshot residue (GSR) analysis, the automatic detection of potential GSR samples can support the task of evidence collection or analysis of residue needed e.g. for a muzzle-to-target firing distance estimation. In this paper we investigate the application of a hyperspectral camera and two well-known Machine Learning algorithms to automatically indicate the potential presence of GSR samples in a scene containing cloth fabrics. For this study we have created and annotated a hyperspectral image dataset consisting of GSR samples present on multiple fabric types. The GSR samples were obtained using two types of ammunition, discharged from two shooting distances. We have investigated two detection scenarios: an unsupervised anomaly detection (with the RX detector) and a supervised pixel classification (with the SVM classifier). Our results show that an accurate detection is possible in both cases. We also note that in this setting the anomaly detection approach usually requires an image normalisation, while the classifier does not require a fabric-specific information. As an addition, we show that the hyperspectral imaging generally outperforms the RGB imaging in terms of GSR detection accuracy. While the actual verification on presence of GSR on the scene requires an analyst and secondary identification methods, the hyperspectral camera with image processing algorithms can be a valuable tool supporting the evidence collection and analysis.