Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems
Thinning Methodologies-A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Feature Subset Selection Using a Genetic Algorithm
IEEE Intelligent Systems
Uniform Crossover in Genetic Algorithms
Proceedings of the 3rd International Conference on Genetic Algorithms
Automatic Detection of Handwriting Forgery
IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Establishing Handwriting Individuality Using Pattern Recognition Techniques
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Individuality of Handwritten Characters
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Analysis of Handwriting Individuality Using Word Features
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Hybrid learning using genetic algorithms and decision trees for pattern classification
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Fast generic selection of features for neural network classifiers
IEEE Transactions on Neural Networks
Internet traffic classification demystified: myths, caveats, and the best practices
CoNEXT '08 Proceedings of the 2008 ACM CoNEXT Conference
A Persian writer identification method using swarm-based feature selection approach
International Journal of Biometrics
Identifying the writer of ancient inscriptions and Byzantine codices. A novel approach
Computer Vision and Image Understanding
| Hi-index | 0.01 |
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.