Enhancing forensic blood detection using hyperspectral imaging and advanced preprocessing techniques
DOI:
https://doi.org/10.1016/j.talanta.2024.127097Keywords:
Dimensional reduction , Forensic blood detection , Hyperspectral image , Image classification , Molecular spectroscopyAbstract
Bloodstains are pivotal in forensic investigations as they can provide crucial DNA information about individuals involved in a crime. Traditional methods for bloodstain detection, including chemical tests and forensic lights, have limitations such as non-specificity to human blood and susceptibility to false positives. In forensic blood detection, molecular spectroscopy is crucial for identifying the unique spectral fingerprints of blood, which arise from its molecular composition. Hyperspectral imaging (HSI) leverages this principle by capturing a wide spectrum of light for each pixel in an image, allowing for the detailed analysis of various substances. HSI has emerged as a promising alternative, offering non-contact, rapid, and cost-effective detection of bloodstains by analyzing the visible and near-infrared electromagnetic spectrum. This study explores the application of HSI for blood detection, addressing challenges such as spectral mixing, time-related changes in bloodstain spectra, and data complexity. The study introduces a novel framework to optimize HSI data, enhancing the accuracy and efficiency of bloodstain classification, called the Fast Extraction (FE) framework. It includes two stages. The main method in the first one is the Enhancing Transformation Reduction (ETR) method to reduce the dimension and complexity of the HSI. The second stage contains a compatible classification model to enhance feature extraction and classification. Our approach is validated using the HyperBlood datasets and many evaluation methods, demonstrating superior performance compared to state-of-the-art deep learning models. It provides high accuracy (97%–100 %) for all HSIs, overcoming various difficulties and blood collection times.References
Indalecio-Céspedes, C. R., et al. (2021). Occult bloodstains detection in crime scene analysis. Forensic Chemistry, 26, 100373. https://doi.org/10.1016/j.forchem.2021.100373
Barni, F., Lewis, S. W., Berti, A., Miskelly, G. M., & Lago, G. (2007). Forensic application of the luminol reaction as a presumptive test for latent blood detection. Talanta, 72(3), 896–913. https://doi.org/10.1016/j.talanta.2006.12.045
Polacco, S., et al. (2019). Luminol reagent control materials in bloodstain pattern analysis: A silicon sol-gel polymer alternative. Forensic Chemistry, 16, 100181. https://doi.org/10.1016/j.forchem.2019.100181
Romaszewski, M., et al. (2021). A dataset for evaluating blood detection in hyperspectral images. Forensic Science International, 320, 110682. https://doi.org/10.1016/j.forsciint.2021.110682
Edelman, G. J., Gaston, E., van Leeuwen, T. G., Cullen, P. J., & Aalders, M. C. G. (2012). Hyperspectral imaging for non-contact analysis of forensic traces. Forensic Science International, 223(1-3), 28–39. https://doi.org/10.1016/j.forsciint.2012.09.012
Al-Alimi, D., et al. (2022). Compression and reinforce variation with convolutional neural networks for hyperspectral image classification. Applied Soft Computing, 116, 108307. https://doi.org/10.1016/j.asoc.2021.108307
Pereira, J. F. Q., et al. (2021). Hierarchical method and hyperspectral images for classification of blood stains on colored and printed fabrics. Chemometrics and Intelligent Laboratory Systems, 212, 104289. https://doi.org/10.1016/j.chemolab.2021.104289
Al-Alimi, D., et al. (2023). IDA: Improving distribution analysis for reducing data complexity and dimensionality in hyperspectral images. Pattern Recognition, 138, 109355. https://doi.org/10.1016/j.patcog.2023.109355
Al-Alimi, D., et al. (2023). ETR: Enhancing transformation reduction for reducing dimensionality and classification complexity in hyperspectral images. Expert Systems with Applications, 215, 119330. https://doi.org/10.1016/j.eswa.2022.119330
Meng, X., et al. (2023). OSCA-finder: Redefining the assay of kidney disease diagnostic through metabolomics and deep learning. Talanta, 254, 124116. https://doi.org/10.1016/j.talanta.2022.124116
Zeng, F., et al. (2023). Rapid detection of white blood cells using hyperspectral microscopic imaging system combined with Multi-data Faster RCNN. Sensors and Actuators B: Chemical, 380, 133342. https://doi.org/10.1016/j.snb.2023.133342
Wang, Q., et al. (2021). A 3D attention networks for classification of white blood cells from microscopy hyperspectral images. Optics & Laser Technology, 139, 106962. https://doi.org/10.1016/j.optlastec.2021.106962
Cardoso Rial, R. (2024). AI in analytical chemistry: Advancements, challenges, and future directions. Talanta, 268, 125345. https://doi.org/10.1016/j.talanta.2023.125345
Rajchl, A., et al. (2010). Stability of nutritionally important compounds and shelf life prediction of tomato ketchup. Journal of Food Engineering, 99(4), 465–471. https://doi.org/10.1016/j.jfoodeng.2010.03.022
Kozlova, E., et al. (2020). Assessment of carboxyhemoglobin content in the blood with high accuracy: Wavelength range optimization for nonlinear curve fitting of optical spectra. Heliyon, 6(12), e05670. https://doi.org/10.1016/j.heliyon.2020.e05670
Saha, D., et al. (2021). Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review. Current Research in Food Science, 4, 28–44. https://doi.org/10.1016/j.crfs.2021.01.002
Lei, Y., et al. (2022). Rapid resolution of types and proportions of broken grains using hyperspectral imaging and optimization algorithm. Journal of Cereal Science, 105, 103456. https://doi.org/10.1016/j.jcs.2022.103456
