Forensic Document Examination: Who Is the Writer?
This work presents a baseline system to automatic handwriting identification based only on graphometric features. Initially a set composed of 12 features was presented and its extraction process demonstrated. In order to evaluate the efficiency of these features, a selection process was applied, and a smaller group composed only of 4 features (GS = Goodness Subset) present the best writer identification rates. Experiments were conducted in order to evaluate the performance, individually and in group, of the graphometric features; and to identify the number of writers that significantly affect the accuracy of the system. The accuracy of the system applied to 100 different writers taking account the GS features set were 84% (TOP1), 96% (TOP5) and 98% (TOP10). These results are comparable to others in the literature on graphometric features. It can be observed that gradually the relation between the number of writers and accuracy is stabilized, and with 200 writers the results are maintained.
KeywordsGraphometry Feature extraction Forensic letter
- 1.Sheikholeslami, G., Srihari, S.N., Govindaraju, V.: Computer aided graphology. In: Proceedings of the 5th International Workshop on Frontiers in Handwriting Recognition, Essex, England, pp. 457–460 (1996)Google Scholar
- 2.Sreejaj, M., Idicula, S.M.: A survey on writer identification schemas. Int. J. Comput. Appl. 26(2), 23–33 (2011)Google Scholar
- 5.Blankers, V., Niels, R., Vuurpijl, L.: Writer identification by means of explainable features: shapes of loops and lead-in strokes. In: Proceedings of the 19th Belgian-Dutch Conference on Artificial Intelligence, pp. 17–24 (2007)Google Scholar
- 8.Amaral, A.M.M.M., Freitas, C.O.A., Bortolozzi, F.: Feature selection for forensic handwriting identification. In: Proceedings of 12th International Conference on Document Analysis and Recognition. Washington: (IAPR), vol. 1, pp. 10–15 (2013)Google Scholar
- 9.Morris, R.N.: Forensic Handwriting Identification: Fundamental Concepts and Principles. Academic Press, Cambridge (2000)Google Scholar
- 11.Franke, K., Rose, S.: Ink-deposition model: the relation of writing and ink deposition processes. In: Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition (IWFHR 2004), pp. 173–178. IEEE Computer Society (2004)Google Scholar
- 14.Bulacu, M., Schomaker, L. Brink, A.: Text-independent writer identification and verification on offline Arabic handwriting. In: Proceedings of the 9th Conference on Document Analysis and Recognition (ICDAR) (2007)Google Scholar
- 18.Siddiqi, I., Vincent, N. Combining global and local features for writer identification. In: Proceedings of the 11th International Conference on Frontiers in Handwriting Recognition, pp. 48–53 (2008)Google Scholar
- 20.Hertel, C. Bunke, H.: A set of novel features for writer identification. In: Proceedings of the 4th International Conference on Audio- and Video-Based Biometric Person Authentication, pp. 679–687 (2003)Google Scholar
- 21.Schlapbach, A., Bunke, H.: Off-line handwriting identification using HMM based recognizers. In: Proceedings of 17th International Conference of the Pattern Recognition – ICPR 2004, vol. 2 (2004)Google Scholar
- 23.Chen, J., Lopresti, D., Kavallieratou, E.: The impact of ruling lines on writer identification. In: 12th International Conference on Frontiers in Handwriting Recognition (2010)Google Scholar
- 24.Freitas, C.O.A., Oliveira, L.S., Bortolozzi, F., Sabourin, R.: Brazilian forensic letter database. In: Proceedings of the 11th International Workshop on Frontiers on Handwriting Recognition (2008)Google Scholar
- 25.Dy, J.G., Broadley, C.E.: Feature subset selection and order identification for unsupervised learning. In: Proceedings of 17th International Conference on Machine Learning, pp. 247–254 (2000)Google Scholar