Unsupervised Clustering of Hyperspectral Paper Data Using t-SNE

• Published in: Journal of imaging Vol. 6; no. 5; p. 29
• Main Authors: Melit Devassy, Binu, George, Sony, Nussbaum, Peter
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 05.05.2020; MDPI
• Subjects: Algorithms; Cameras; Classification; Cluster analysis; Clustering; Cultural heritage; Data analysis; Datasets; forensic document analysis; forensic paper analysis; Forensic sciences; Forgery; Fourier transforms; hyperspectral dimensionality reduction; Hyperspectral imaging; hyperspectral unsupervised clustering; Methods; Narrowband; Nondestructive testing; Software; Spectrum analysis; t-SNE; Vector quantization

For a suspected forgery that involves the falsification of a document or its contents, the investigator will primarily analyze the document’s paper and ink in order to establish the authenticity of the subject under investigation. As a non-destructive and contactless technique, Hyperspectral Imaging...