PENGENALAN WAJAH MENGGUNAKAN METODE BIOMIMETIC PATTERN RECOGNITION
Daftar Isi:
- Biometric authentication systems are widely used in various ways. One of the most used biometric systems is the face. Face recognition is divided into three processes, namely pre-processing, feature extraction, and classification. This paper combines the Linear Discriminant Analysis (LDA) method as feature extraction because it is resistant to changing image conditions and Hyper Sausage Neuron Network (HSNN) as a classification because able to overcome high false acceptance problems on traditional pattern recognition. The purpose of this paper is to produce a face recognition architecture using LDA-HSNN, produce face recognition software using LDA-HSNN, and know the accuracy of LDA-HSNN for face recognition. This study uses secondary data from the face94 database and has a JPEG format. This study was tested using many different training image data, parameter α and 684 image samples of test data. Based on the results of the study, it was concluded that the combination of the LDA and HSNN methods was able to recognize faces with an accuracy of 92.69%.