Comparison of Ink Classification Capabilities of Classic Hyperspectral Similarity Features

Ink classification is an active topic in historic and forensic document analysis. In this work, we compared the ink classification capabilities of five commonly used and wellproven similarity measures for classification of hyperspectral imaging (HSI). They are Spectral Angle Mapper (SAM), Spectral Correlation Mapper (SCM), Euclidean Distance (ED), Spectral Information Divergence (SID) and Binary Encoding (BE). These techniques were well explored in different fields of HSI; however, they are not investigated in the field of ink classification. This study reveals the ink classification capabilities of these similarity measures. A combination of different types and colors of inks from different manufactures were used to create sample text. The SAM obtained higher accuracy compared to other methods and also identified that, inks that have nearly similar spectral signatures, cause a decline in accuracies due to misclassification between similar classes.

[1]  André Braz,et al.  Raman spectroscopy for forensic analysis of inks in questioned documents. , 2013, Forensic science international.

[2]  Liren Zhang,et al.  The principle and application of hyperspectral imaging technology in detection of handwriting , 2017, 2017 9th International Conference on Advanced Infocomm Technology (ICAIT).

[3]  M. Xie,et al.  Classification and dating of black gel pen ink by ion-pairing high-performance liquid chromatography. , 2006, Journal of chromatography. A.

[4]  Karmon Vongsy,et al.  A comparative study of spectral detectors , 2011, 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[5]  Jon Yngve Hardeberg,et al.  Ink classification and visualisation of historical manuscripts: Application of hyperspectral imaging , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[6]  K. Savage,et al.  Hyperspectral imaging of gel pen inks: an emerging tool in document analysis. , 2014, Science & justice : journal of the Forensic Science Society.

[7]  Chein-I. Chang.  Spectral information divergence for hyperspectral image analysis , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[8]  Sim Heng Ong,et al.  A New Perspective on Material Classification and Ink Identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Muhammad Naeim Mohamad Asri,et al.  Forensic Analysis of Gel Pen Inks using Hyperspectral Imaging coupled with Chemometric Procedures , 2019, Arab Journal of Forensic Sciences & Forensic Medicine.

[10]  P. R. Meneses,et al.  Spectral Correlation Mapper ( SCM ) : An Improvement on the Spectral Angle Mapper ( SAM ) , 2000 .

[11]  Ajmal S. Mian,et al.  Hyperspectral Imaging for Ink Mismatch Detection , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[12]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[13]  Thomas L. Ainsworth,et al.  Modeling data manifold geometry in hyperspectral imagery , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Donald R. Scott,et al.  Effects of binary encoding on pattern recognition and library matching of spectral data , 1988 .

[15]  R. Poppi,et al.  Discriminating blue ballpoint pens inks in questioned documents by Raman imaging and mean-field approach independent component analysis (MF-ICA) , 2019, Microchemical Journal.

[16]  Maria Fernanda Pimentel,et al.  Classification of blue pen ink using infrared spectroscopy and linear discriminant analysis , 2013 .

[17]  J. Gower.  Properties of Euclidean and non-Euclidean distance matrices , 1985 .

[18]  Ulrich Panne,et al.  Multivariate classification of pigments and inks using combined Raman spectroscopy and LIBS , 2012, Analytical and Bioanalytical Chemistry.

[19]  Maria Fernanda Pimentel,et al.  Evaluating the potential of near infrared hyperspectral imaging associated with multivariate data analysis for examining crossing ink lines. , 2019, Forensic science international.

[20]  Lin Yan,et al.  Large-Area Gap Filling of Landsat Reflectance Time Series by Spectral-Angle-Mapper Based Spatio-Temporal Similarity (SAMSTS) , 2018, Remote. Sens..