Artículos de revistas
Writer verification based on simple graphemes and extreme learning machine approaches
Autor
Mora, Marco
Vásquez, A.
Aubin, Verónica
Salazar, E.
Barrientos, Ricardo
Hernández-García, Ruber
Vilches-Ponce, Karina
Institución
Resumen
Traditional literature presents complex biometric sources, descriptors, and classifiers to solve the writer's verification problem. The simple graphemes have been studied recently considering classifiers such as multilayer perceptron, support vector machine and convolutional neural network, which allow a high level of performance but with high computational cost in the training. In this paper, we propose the use of extreme learning neural networks to verify the writer identity based on simple graphemes with the aim of achieve a better descriptor performance in a less training time. The proposal allows verify peoples identity through the analysis of handwritten text in order to fakes detect, authorship identification, fakes, threats and thefts in documents. The experimental results show that this type of classifiers achieve a rate of success greater to the 95% for all five characters in the problem addressed, but with significantly less training times than traditionally used techniques.