Establishing Handwriting Individuality Using Pattern Recognition Techniques
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
ImprovingWriter Identification by Means of Feature Selection and Extraction
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
A writer identification system for on-line whiteboard data
Pattern Recognition
Writer identification using global wavelet-based features
Neurocomputing
Writer identification using fractal dimension of wavelet subbands in gabor domain
Integrated Computer-Aided Engineering
Text-Independent writer identification based on fusion of dynamic and static features
IWBRS'05 Proceedings of the 2005 international conference on Advances in Biometric Person Authentication
Online text-independent writer identification based on stroke's probability distribution function
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Off-line hand written input based identity determination using multi kernel feature combination
Pattern Recognition Letters
Identifying the writer of ancient inscriptions and Byzantine codices. A novel approach
Computer Vision and Image Understanding
| Hi-index | 0.00 |
The objective of this paper is to present a number offeatures that can be extracted from handwritten digits andused for author verification or identification of a person'shandwriting. The features under consideration are mainlycomputational features some of which cannot be easilyevaluated by humans. On the other hand, these featurescan be extracted by computer algorithms with a highdegree of accuracy.The eleven features used are described. All featureswere appropriately binarized so that binary featurevectors of constant lengths could be formed. These vectorswere then used for author discrimination, using theHamming distance measure. For this task a writerdatabase consisting of 15 writers was created. Each writerwas asked to write random strings of 0 to 9 at least 10times. The results indicate that the combined featureswork well at discriminating writers and warrant furtherdetailed investigation.Although the set of features was designed for dealing withhandwritten digits (as may be written on cheques), it mayalso be used for isolated alphabetic characters.