Discriminative power of features used by forensic document examiners in the analysis of handwriting
Forensic document examintation of handwriting to determine the authorship of questioned documents has been in use for more than 100 years. However, in recent court cases the acceptability of forensic document analysis has been successfully challenged. It has been pointed that the techniques, althoug...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
2008
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/2515 |
| _version_ | 1826113260905037824 |
|---|---|
| author | Pervouchine, Vladimir |
| author2 | Leedham Charles Graham |
| author_facet | Leedham Charles Graham Pervouchine, Vladimir |
| author_sort | Pervouchine, Vladimir |
| collection | NTU |
| description | Forensic document examintation of handwriting to determine the authorship of questioned documents has been in use for more than 100 years. However, in recent court cases the acceptability of forensic document analysis has been successfully challenged. It has been pointed that the techniques, although intuitively reasonable, lack strong scientific foundation. In this thesis a study of discriminative power of a number of character-level features is presented. The features correspond to those used by forensic document examiners. It was shown that most of the studied features indeed possess discriminative power and hence their use in forensic analysis of handwriting is justified. |
| first_indexed | 2024-10-01T03:20:18Z |
| format | Thesis |
| id | ntu-10356/2515 |
| institution | Nanyang Technological University |
| last_indexed | 2024-10-01T03:20:18Z |
| publishDate | 2008 |
| record_format | dspace |
| spelling | ntu-10356/25152023-03-04T00:39:33Z Discriminative power of features used by forensic document examiners in the analysis of handwriting Pervouchine, Vladimir Leedham Charles Graham School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Forensic document examintation of handwriting to determine the authorship of questioned documents has been in use for more than 100 years. However, in recent court cases the acceptability of forensic document analysis has been successfully challenged. It has been pointed that the techniques, although intuitively reasonable, lack strong scientific foundation. In this thesis a study of discriminative power of a number of character-level features is presented. The features correspond to those used by forensic document examiners. It was shown that most of the studied features indeed possess discriminative power and hence their use in forensic analysis of handwriting is justified. DOCTOR OF PHILOSOPHY (SCE) 2008-09-17T09:04:37Z 2008-09-17T09:04:37Z 2006 2006 Thesis Pervouchine, V. (2006). Discriminative power of features used by forensic document examiners in the analysis of handwriting. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/2515 10.32657/10356/2515 Nanyang Technological University application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Pervouchine, Vladimir Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title | Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title_full | Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title_fullStr | Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title_full_unstemmed | Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title_short | Discriminative power of features used by forensic document examiners in the analysis of handwriting |
| title_sort | discriminative power of features used by forensic document examiners in the analysis of handwriting |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition |
| url | https://hdl.handle.net/10356/2515 |
| work_keys_str_mv | AT pervouchinevladimir discriminativepoweroffeaturesusedbyforensicdocumentexaminersintheanalysisofhandwriting |