ABSTRAKSI: Ada banyak metode-metode yang telah digunakan dalam mendeteksi wajah, Neural Network, Principal Component Analysis (PCA), dan Independent Component Analysis (ICA) telah banyak dipelajari. ICA menghasilkan gambar dasar yang independent (independent image basis) yang mempertegas bagian tepi dari suatu gambar. Hal ini sudah banyak dipakai dalam pengenalan wajah [1]. Support Vector Machine (SVM) adalah metode learning mechine yang bekerja atas prinsip Structural Risk Minimization (SRM) dengan tujuan menemukan hyperlane terbaik yang memisahkan dua buah class pada input space [7]. ICA dan SVM dapat dikombinasikan untuk mempelajari masalah-masalah dalam pendeteksian wajah. Kombinasi ICA dan SVM diharapkan menghasilkan performa yang lebih baik dibandingkan dengan metoda-metoda lainnya yang sudah cukup lama digunakan.
Kata Kunci : pendeteksian wajah, Independent Component Analysis (ICA),ABSTRACT: There are many methods that have been used in face detection, Neural Network, Principal Component Analysis (PCA), and Independent Component Analysis (ICA) have been studied. Independent ICA basis emphasizes the edge information in image.ICA algorithms have been succesfully used in face recognation [1]. SVM is learning Machines methods based on Structural Risk Minimization (SRM) principles in order to find the best hyperplane which separates two classes in input space [7]. ICA and SVM can be combined to learn the face detection problem. The combination of ICA and SVM is hoped to prodeced better performance instead of the other method that have been used.Keyword: face detection, Independent Component Analysis (ICA), Support