Técnicas de processamento de imagens para localização e reconhecimento de faces / Image processing techniques for faces location and recognition

AUTOR(ES)
DATA DE PUBLICAÇÃO

2006

RESUMO

Biometry is the science of measuring and analyzing biomedical data. Many works in this field have explored the characteristics of human beings, such as digital fingerprints, iris, and face to develop biometric systems, employed in various aplications (security monitoring, ubiquitous computation, robotic). Face identification and recognition are very apealing biometric techniques, as it it intuitive and less invasive than others. Many works in this field are only concerned with locating the face of an individual (for counting purposes), while others try to identify people from faces. The objective of this work is to develop a biometric system that could identify and recognize faces. The work can be divided into two major stages: (1) Locate and track in a sequence of images (frames), as well as separating the tracked region from the image; (2) Recognize a face as belonging to a certain individual. In the former, faces are captured from frames of a video camera by a motion analysis system (based on substraction of frames), capable of finding, tracking and croping faces from images of individuals. The later, consists of elements for data reductions (Principal Component Analysis - PCA), feature extraction (Gabor wavelets) and face classification (Euclidean distance and Support Vector Machine - SVM). Two faces databases have been used: FERET and a "home-made" one. Tests have been undertaken so as to assess the systems recognition capabilities. The experiments have shown that the technique exhibited a satisfactory performance, with success rates of 91.97% and 100% for the FERET and the "home-made" databases, respectively.

ASSUNTO(S)

reconhecimento de face wavelet de gabor rastreamento de face svm face tracking face recognition svm gabor wavelet

ACESSO AO ARTIGO

Documentos Relacionados