Pattern classification: a unified view of statistical and neural approaches
Pattern classification: a unified view of statistical and neural approaches
Comparison of normalization methods for character recognition
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Establishing Handwriting Individuality Using Pattern Recognition Techniques
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Individuality Analysis of Online Kanji Handwriting
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Online writer verification using kanji handwriting
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
| Hi-index | 0.00 |
In this paper a study of some structural features of hand-writtenletter a' is presented. The features under considerationare structural, style and formation features documentexaminer's use when studying a questioned document to determineits authorship or authenticity.Feature extraction algorithms for the feature set were developedto perform the extraction procedure automatically.The estimate of feature consistency is introduced and measuredfor each extracted feature. The extracted feature setis analyzed for linear independency and ability to be usedfor separation of author classes (i.e. authorship decision).The results on a set of 18 authors with approximately 40 letter'a's per author indicates a high level of consistency anddiscrimination ability for most of the features analysed.