Biometrics is the study of automated method to recognize or identify people based on one or more parts of the human body or the behavior of man himself Facial image recognition is the process ofmatching between the characteristics of the image query image with the characteristics of the training image stored in a database (image library) that implement it through a mathematical transformation that is by using wavelet transform. The image is a spatial dimension that contains the color information and does not depend on the time consisted of a set of image dots, called pixels (picture element). K-NearestNeighbour(kNN) is a method that uses a supervised algorithm where the result of new instancequery classified based on kNN majority of categories that works based on the shortest distance from the query instance to the training sample to determine its kNN. The wavelet transform is used as a method of feature extraction as well as reduce the dimension of the input image with 3 levels of wavelet transform to generate multi-resolution representation. Decomposition of facial images using wavelet transform produces a number of subimage wich consists of image and detail images approach. The result of wavelet transform is used as input for classification. Classification system with a simple method ofk-nearest neighbor (k-nn) to determine the identity of a face image with the threshold value of accuracy used in this study is 95%.
Copyrights © 2009