Applying forensic features on writer identification

Título:	Applying forensic features on writer identification
Autores/as:	Travieso González, Carlos Manuel Alonso, Jesus B. Vasquez, Jose L. Dutta, Malay Kishore Singh, Anushikha
Clasificación UNESCO:	3307 Tecnología electrónica
Palabras clave:	Writing , Feature extraction , Signal processing , Signal processing algorithms , Artificial neural networks , Proposals , Indexes, handwritten identification , image processing , pattern recognition
Fecha de publicación:	2017
Publicación seriada:	2017 4th International Conference on Signal Processing and Integrated Networks, SPIN 2017
Conferencia:	4th International Conference on Signal Processing and Integrated Networks, SPIN 2017
Resumen:	This work present new parameters based on biometrie handwritten information for the writer identification. The feature extraction is developed by new algorithms based on image processing techniques. The handwritten parameters will be classified by artificial neural network and fusion strategy in order to increase the accuracy. After experiments, and using a dataset composed by 100 writers, this proposal reaches an accuracy of 82.7%
URI:	http://hdl.handle.net/10553/43950
ISBN:	9781509027972
DOI:	10.1109/SPIN.2017.8050015
Fuente:	2017 4th International Conference on Signal Processing and Integrated Networks, SPIN 2017 (8050015), p. 572-577
Colección:	Actas de congresos

Vista completa