Pengenalan Citra Wajah Dengan Menggunakan Transformasi Wavelet Diskrit dan Jaringan Saraf Tiruan Back-Propagation

• Main Author: Suhendry Effendy
• Format: Article
• Language: English
• Published: Bina Nusantara University 2010-12-01
• Series: ComTech
• Subjects: face recognition, discrete wavelet transformation, artificial neural network, back-propagation
• Online Access: https://journal.binus.ac.id/index.php/comtech/article/view/2569

This paper discusses the facial image recognition system using Discrete Wavelet Transform and back-propagation artificial neural network. Discrete Wavelet Transform processes the input image to obtain the essential features found on the face image. These features are then classified using an back-propagation artificial neural network for the input image to be identified. Testing the system using facial images in AT & T Database of Faces of 400 images comprising 40 facial images of individuals and web-camera catches as many as 100 images of 10 individuals. The accuracy of level of recognition on AT & T Database of Faces reaches 93.5%, while the accuracy of level of recognition on a web-camera capture images up to 96%. Testing is also done on image of AT & T Database of Faces with given noise. Apparently the noise in the image does not give meaningful effect on the level of recognition accuracy.