Pervouchine, Vladimir

Leedham, Graham

2007

In this paper we present a study of structural features of handwriting extracted from three characters "d", "y", and "f" and grapheme "th". The features used are based on the standard features used by forensic document examiners. The process of feature extraction is presented along with the results. Analysis of the usefulness of features was conducted via searching the optimal feature sets using the wrapper method. A neural network was used as a classifier and a genetic algorithm was used to search for optimal feature sets. It is shown that most of the structural micro features studied, do possess discriminative power, which justifies their use in forensic analysis of handwriting. The results also show that the grapheme possessed significantly higher discriminating power than any of the three single characters studied, which supports the opinion that a character form is affected by its adjacent characters.

Pattern Recognition, 40(3), p. 1004-1013

1873-5142

0031-3203

https://hdl.handle.net/1959.11/9256

Elsevier Ltd

Extraction and analysis of forensic document examiner features used for writer identification

Journal Article

Publication