Detecting semen stains on fabrics using near infrared hyperspectral images and multivariate models

Identification of semen stains is a critical step in evidence analysis in cases of sexual assaults (rape, child molestation, sexual harassments, etc). Presumptive and confirmatory methodologies that are nondestructive and can be used at crime scenes are extremely needed to help forensic experts to collect useful evidences without compromising the integrity of the samples. In this work, we put forward the high potential of a fast, nondestructive and noninvasive methodology like Near Infrared Hyperspectral Imaging (HSI-NIR), together with adequate multivariate methodologies for exploratory data analysis and classification. Due to the high absorption of the substrate, an exhaustive data analysis is performed in order to test the most suitable tool for the detection and discrimination of semen stains in diverse fabrics. Samples of human semen, lubricants, breast milk and animal semen were placed on fabrics of different colors and compositions to create a stain and hyperspectral images were acquired. As identification tools, Principal Component Analysis and MCR-ALS were used. Moreover, Classification techniques such as PLS-DA, sPLS-DA and SVM-DA were used in order to differentiate human semen from other substances. Although the methodology developed depend on the substrate used, it has been proven that HSI-NIR can be used as presumptive and confirmatory method of analysis in the search for semen stains.