A dataset for evaluating blood detection in hyperspectral images

The sensitivity of imaging spectroscopy to haemoglobin derivatives makes it a promising tool for detecting blood. However, due complexity and high dimensionality hyperspectral images, the development blood detection algorithms is challenging. To facilitate their development, we present new dataset. This dataset, published in accordance open access mandate, consist multiple scenarios with varying levels complexity. It allows test performance Machine Learning methods relation different acquisition environments, types background, age presence other blood-like substances. We explored dataset experiments. used target algorithm based on well-known Matched Filter detector. Our results discussion highlight challenges data form reference further works.