An Analysis of Haar Wavelet Transformation for Androgenic Hair Pattern Recognition

identify criminal or pedophile in online child pornography images and video is a challenging task when the faces and other distinguish features are not shown. To address these kind of problems, the system of recognition using androgenic hair pattern is being developed. The system of recognition presented in this paper used three main parts of methods, pre-processing methods, feature extraction with Haar Wavelet Transform level 1 decomposition and classification using Nearest Neighbor. Using 400 images of lower right legs with controlled condition, the system was analyzed. The Haar Wavelet Transformation for level 1 decomposition gave 83.48 % of average recognition precision when using 10-fold cross validation with nearest neighbor classification.