Yüz görüntülerinden cinsiyet tahmini

Studies on facial biometrics is vital as they are the driving force behind the development of applications in public spaces. By the help of these studies, researchers have been able to make gender recognition with higher accuracy rates. However, to perform these tasks with computers, real time and large scale applications are needed. This study aims at which wavelet filters are more useful for extracting meaningful facial features by using frontal face images.In this study, an application using 103 wavelet filters with the help of frontal face images to perform better gender classification is developed. The accuracy rate of wavelet filters is tested using discrete wavelet transform and gray level co-occurrence matrix that produces 103 feature sets. As classifier, support vector machines are used. Keywords: Gender Recognition, Discrete Wavelet Transform, Gray Level Co-Occurrence Matrix, Support Vector Machines.