Operador morfológico pecstrum en FPGA para aplicaciones de biometría

Biometric recognition has gained importance in environments that require people identification. Biometric system aim for people identification using different unique, physiological, time- invariant characteristics for each person such as digital prints, face, iris and retina detection, hand geometry...

Descripción completa

Detalles Bibliográficos
Autor: MIGUEL ANGEL MORENO CEDEÑO
Tipo de recurso: tesis de maestría
Estado:Versión aceptada para publicación
Fecha de publicación:2011
País:México
Institución:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositorio:Repositorio Institucional del INAOE
Idioma:español
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/707
Acceso en línea:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/707
Access Level:acceso abierto
Palabra clave:info:eu-repo/classification/Registro de imagen/Image registration
info:eu-repo/classification/Biometría/Biometrics
info:eu-repo/classification/Field programable gate array/Field programable gate array
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/22
info:eu-repo/classification/cti/2203
Descripción
Sumario:Biometric recognition has gained importance in environments that require people identification. Biometric system aim for people identification using different unique, physiological, time- invariant characteristics for each person such as digital prints, face, iris and retina detection, hand geometry, voice, hand shape, palm print. The hand shape based techniques use biometric characteristic such as finger and palm length and width, fingers to palm size ratio, palm print information, palm shape, joint finger width or a combination between them. One of these techniques uses the pattern spectrum as a characteristic extractor to obtain hand shape quantitative information. Position and rotation invariant property of pecstrum allows the user to place the hand without extra restrictions. The Pattern spectrum consists on the successive application of binary erosion and dilatation based opening filters, using in each step a growing structuring element. The erosion and dilatation functions used in pecstrum for large structuring elements are computationally intensive, the algorithms use long time to execute, and it causes an excessive time computing. The use of an FPGA allows to obtain a compact system since the complete electronic for control and image processing may be placed in one circuit. This thesis raises the implementation of the pecstrum algorithm on a FPGA to process binary images with the purpose of offering a competitive calculation time.