iVision HHID: Handwritten hyperspectral images dataset for benchmarking hyperspectral imaging-based document forensic analysis

Recent Advances in Counterfeit Art, Document, Photo, Hologram, and Currency Detection Using Hyperspectral Imaging

“…While the latest research incorporated in this review was published in 2020, it must be noted that the vast majority of recent studies that were available were excluded following inclusion and exclusion criteria. New studies are continuously being introduced to this field, including the follow-up studies of research incorporated in this review [ 191 , 192 ]. A more detailed breakdown of the accuracies, including those of each topic classification, wavelength, processing method, as well as their calculations can be found in Supplementary Materials, Figures S2–S24 and Supplementary Materials, Tables S1–S22 .…”

Ink Mismatch Detection Using Unsupervised Learning

“…The collected documents were scanned with Imec SNAPSCAN-VNIR hyperspectral camera resulting in an image size of 512 × 620 pixels containing 149 bands. The spectral frequency for the scanning device ranges from 478 to 901 nm [18]- [20]. In this research, the dataset used comprises of one image…”

Forensic applications of hyperspectral imaging technique: a narrative review

“…One of the main practical HSI limitations in this context is the low availability of a reference dataset. Starting from this assumption in the work published by Islam et al 16 the authors introduced a dataset of hyperspectral images about handwritten documents drawn up by 54 individuals, whose age and gender were known. Each person was required to write 28 sentences, containing upper and lower-case letters using 12 different types of pens (all blue in colour).…”