Identificação biométrica de pessoas via características dos seios paranasais obtidas de tomografias computadorizadas

• Ano de defesa: 2016
• Autor(a) principal: Souza Júnior, Luis Antonio [UNESP]
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual Paulista (Unesp)
• Palavras-chave em Português: Biometrics; Paranasal sinuses; Computed tomography; Forensics identification; Biometria; Tomografia computadorizada; Seios paranasais; Identificação forense
• Link de acesso: http://hdl.handle.net/11449/143879

Biometric identification of people in the forensic field is constantly being studied to facilitate and improve the identification methods through the evaluation of several structures that can be used as biometric features. The paranasal sinuses, bone cavities present in the skull, have high individuality and permanence and can be used in forensic biometric systems. The X-rays and Computed Tomography are modalities of medical examinations used for the digital representation of the paranasal sinuses. X-rays images as a tool to obtain characteristics of the paranasal sinuses are highly applicable in the related works, however, in this imaging modality, some disadvantages, such as low quality resolution, make these structures harder to acquire. With computed tomography representation, a new evaluation can be performed to obtain the paranasal sinuses features, knowing that this exam modality generates an image sequence with higher quality, making the paranasal sinuses segmentation and feature extraction simpler, intuitive and precise, facilitating its use in biometric recognition systems. The objective of this master’s dissertation was the development of a new human identification method that uses paranasal sinuses structures as biometric features, obtained from computed tomography images. This method proposes significant advances, specially on the segmentation and features extraction stages, once the segmentation of the paranasal sinuses structures is performed automatically. The characteristics proposed for the feature descriptors are based on the region and shape of the paranasal structures. The experimental results obtained from a database composed by 310 computed tomography images presented that the automatic method proposed in this dissertation showed 88.52% of frontal sinuses segmentation and 79.30% of correct maxillary sinuses segmentation using the KAPPA coefficient. Relative to the persons identification, the proposed method presented in the best case 8.99% of EER. Therefore, in this master’s dissertation, it was concluded that: the face sinuses, and in particular the frontal sinuses, can be used with success for the forensic human identification; for the human identification based on the frontal sinuses the shape descriptors are more efficient than the region descriptors, while that for the human identification based on maxillary sinuses, the shape descriptors do not presented high discrimination performance and; it is possible to automate the frontal and maxillary sinuses segmentation process using computed tomography images.