Towards an Automatic Frontal Sinus Identification System

A. N. MaranaD. Y. OuraT. YamamotoF. P. S. FalgueraJ. R. Falguera

It has been established in prior investigations that the radiographic pattern of frontal sinus ishighly variable and unique for every individual. This has stimulated the proposition of measurementsof the frontal sinus pattern, obtained from x-ray films, for manual human skeletal identification. The goal of this project is to investigate the best descriptors to be used in an automatic frontal sinus identification system, which is being implemented to allow automatic human identification based on this biometric trait. This paper proposes a frontal sinus representation and description based on frontal sinus shape and presents results obtained with experiments carried out on a database with 52 anteroposterior radiograph images. The results obtained (11,56% of equal error rate) are promising. There are relatively few studies reported in the literature about automatic human identification based on frontal sinus. Therefore, the results presented in this paper can be considered a relevant contribution.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: