Image Processing Techniques For Faces Location And Recognition
(Almeida, Osvaldo Cesar Pinheiro de)
Image processing techniques for faces location and recognitionBiometry is the science of measuring and analyzing biomedical data.Many works in this field have explored the characteristics of humanbeings, such as digital fingerprints, iris, and face to developbiometric systems, employed in various aplications (securitymonitoring, ubiquitous computation, robotic). Face identification andrecognition are very apealing biometric techniques, as it it intuitiveand less invasive than others. Many works in this field are onlyconcerned with locating the face of an individual (for countingpurposes), while others try to identify people from faces. Theobjective of this work is to develop a biometric system that couldidentify and recognize faces. The work can be divided into two majorstages: (1) Locate and track in a sequence of images (frames), as wellas separating the tracked region from the image; (2) Recognize a faceas belonging to a certain individual. In the former, faces are capturedfrom frames of a video camera by a motion analysis system (based onsubstraction of frames), capable of finding, tracking and croping facesfrom images of individuals. The later, consists of elements for datareductions (Principal Component Analysis - PCA), feature extraction(Gabor wavelets) and face classification (Euclidean distance andSupport Vector Machine - SVM). Two faces databases have been used:FERET and a \"home-made\" one. Tests have been undertaken so as toassess the system\'s recognition capabilities. The experiments haveshown that the technique exhibited a satisfactory performance, withsuccess rates of 91.97% and 100% for the FERET and the \home-made\ databases, respectively.
Resumos Relacionados
- On Animation
- Effects Of Diabetes
- Biometrics: Technology For Distinguishing Traits
- Abstract Of Sex Without Love
- Artificial Intelligence
|
|
