[2Yin5] インタラクティブ2

[2Yin5-18] Identification of writing instrument inks by mid-infrared hyperspectral imaging and machine learning.

〇Shigeru SUGAWARA Sugawara¹ (1.National Research Institute of Police Science)

Keywords:Machine Learning, Hyperspectral Imaging, Infrared Spectra, Forensic Document Examination, Visualization

Machine-learning was applied to the automation of data analysis of mid-infrared hyperspectral imaging. It was verified whether the distribution of five types of black marking pens on recycled paper could be visualized accurately. The measurement results of blackened circles were used as training data, and the measurement results of the cross letters and the all-pens’-sample were used as verification data. First, the difference spectra were calculated for the spectra and its second derivative. Next, the principal component score was obtained by the principal component analysis. Classification accuracy was 94% by using the second discriminant analysis. The distribution of ink's difference of the crossed lines could be visualized accurately. For the all-pens'-sample, although there were some misidentifications, the ink distribution could be identified with some accuracy.