A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis
In forensic document analysis, the authenticity of a document must be properly checked in the context of suspected forgery. Hyperspectral Imaging (HSI) is a non-invasive way of detecting fraudulent papers in a multipage document. The occurrence of a forged paper in a multi-page document may have a s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9661320/ |
| _version_ | 1818744467500302336 |
|---|---|
| author | Jobin Francis Baburaj Madathil Sudhish N. George Sony George |
| author_facet | Jobin Francis Baburaj Madathil Sudhish N. George Sony George |
| author_sort | Jobin Francis |
| collection | DOAJ |
| description | In forensic document analysis, the authenticity of a document must be properly checked in the context of suspected forgery. Hyperspectral Imaging (HSI) is a non-invasive way of detecting fraudulent papers in a multipage document. The occurrence of a forged paper in a multi-page document may have a substantial difference from rest of the papers in its age, type, color, texture, and so on. Each pixel in an HSI data can be used as the material fingerprint for the spatial point it corresponds to. Hence, hyperspectral data of paper samples made of the same substance have similar characteristics and can be grouped into a single cluster. Similarly, paper samples made of different substances have different spectral properties. This paper relies on this heuristic and proposes a tensor based clustering framework for hyperspectral paper data, with an application to detect the forged papers in multi-page documents. Information embedded in the hyperspectral patches of the papers to be clustered is arranged into individual lateral slices of a third-order tensor in this framework. Further, this work employs the self-expressiveness property of submodules and an objective function is formulated to extract self-expressive representation tensor with low multirank and f-diagonal structure. Objective function of the proposed method incorporates <inline-formula> <tex-math notation="LaTeX">$l_{\frac {1}{2}}$ </tex-math></inline-formula>-induced Tensor Nuclear Norm (TNN) and <inline-formula> <tex-math notation="LaTeX">$l_{\frac {1}{2}}$ </tex-math></inline-formula> regularization to impart better low rankness and f-diagonal structure to the representation tensor. Experimental results of the proposed method were compared to the state-of-the-art subspace clustering approaches. The results demonstrate improved performance of the proposed method over the existing clustering algorithms. |
| first_indexed | 2024-12-18T02:44:46Z |
| format | Article |
| id | doaj.art-9bed8a4b773d46f2a96c8d661826d93a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T02:44:46Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9bed8a4b773d46f2a96c8d661826d93a2022-12-21T21:23:34ZengIEEEIEEE Access2169-35362022-01-01106194620710.1109/ACCESS.2021.31378699661320A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document AnalysisJobin Francis0Baburaj Madathil1https://orcid.org/0000-0003-3151-9270Sudhish N. George2https://orcid.org/0000-0002-0886-9478Sony George3https://orcid.org/0000-0001-8436-3164Department of Electronics and Communication Engineering, National Institute of Technology Calicut, Calicut, IndiaDepartment of Electronics and Instrumentation Engineering, Government Engineering College Kozhikode, Calicut, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology Calicut, Calicut, IndiaDepartment of Computer Science, Norwegian University of Science and Technology, Gjøvik, NorwayIn forensic document analysis, the authenticity of a document must be properly checked in the context of suspected forgery. Hyperspectral Imaging (HSI) is a non-invasive way of detecting fraudulent papers in a multipage document. The occurrence of a forged paper in a multi-page document may have a substantial difference from rest of the papers in its age, type, color, texture, and so on. Each pixel in an HSI data can be used as the material fingerprint for the spatial point it corresponds to. Hence, hyperspectral data of paper samples made of the same substance have similar characteristics and can be grouped into a single cluster. Similarly, paper samples made of different substances have different spectral properties. This paper relies on this heuristic and proposes a tensor based clustering framework for hyperspectral paper data, with an application to detect the forged papers in multi-page documents. Information embedded in the hyperspectral patches of the papers to be clustered is arranged into individual lateral slices of a third-order tensor in this framework. Further, this work employs the self-expressiveness property of submodules and an objective function is formulated to extract self-expressive representation tensor with low multirank and f-diagonal structure. Objective function of the proposed method incorporates <inline-formula> <tex-math notation="LaTeX">$l_{\frac {1}{2}}$ </tex-math></inline-formula>-induced Tensor Nuclear Norm (TNN) and <inline-formula> <tex-math notation="LaTeX">$l_{\frac {1}{2}}$ </tex-math></inline-formula> regularization to impart better low rankness and f-diagonal structure to the representation tensor. Experimental results of the proposed method were compared to the state-of-the-art subspace clustering approaches. The results demonstrate improved performance of the proposed method over the existing clustering algorithms.https://ieeexplore.ieee.org/document/9661320/Forensic document analysishyperspectral imaging (HSI)clusteringself-expressiveness property |
| spellingShingle | Jobin Francis Baburaj Madathil Sudhish N. George Sony George A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis IEEE Access Forensic document analysis hyperspectral imaging (HSI) clustering self-expressiveness property |
| title | A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis |
| title_full | A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis |
| title_fullStr | A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis |
| title_full_unstemmed | A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis |
| title_short | A Comprehensive Tensor Framework for the Clustering of Hyperspectral Paper Data With an Application to Forensic Document Analysis |
| title_sort | comprehensive tensor framework for the clustering of hyperspectral paper data with an application to forensic document analysis |
| topic | Forensic document analysis hyperspectral imaging (HSI) clustering self-expressiveness property |
| url | https://ieeexplore.ieee.org/document/9661320/ |
| work_keys_str_mv | AT jobinfrancis acomprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT baburajmadathil acomprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT sudhishngeorge acomprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT sonygeorge acomprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT jobinfrancis comprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT baburajmadathil comprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT sudhishngeorge comprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis AT sonygeorge comprehensivetensorframeworkfortheclusteringofhyperspectralpaperdatawithanapplicationtoforensicdocumentanalysis |