Yerel İki̇li̇ Örüntü Ve Yönlü Gradyant Hi̇stogrami Kullanilarak Yüz Görüntüleri̇nden Ci̇nsi̇yet Tahmi̇ni̇

Abstract

Gender prediction from facial images can be used in a large number of applications including human-computer interaction, customer information measurement, access control, etc. Furthermore, it can substantially effect on many fields, such as security systems, biometric authentication, medical imaging systems, demographic studies, content based searching, and surveillance system. In this study, we proposed to use Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG) as the feature extractor and k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) as the classifier in order to predict the gender of the people from facial images. We tested the proposed method in FERET and UTD databases. We used leave-one-out approach as the cross validation technique. The results are promising.

Sex estimation from biometric face photos for forensic purposes

“…It can also greatly affect many areas including but not limited to security systems, biometric authentication, medical imaging systems, demographic studies, contextual search, and surveillance systems. 3…”

“…It can also greatly affect many areas including but not limited to security systems, biometric authentication, medical imaging systems, demographic studies, contextual search, and surveillance systems. 3 Sex estimation studies are generally performed on the skeleton, and specific studies on facial images are rarely encountered in the literature. Skeletal studies focused more on the skull.…”

“…On the other hand, this is difficult for computers that the modern world is connected to. 3 In facial expression or identification studies, fast and reliable sex estimation from human facial images is always a remarkable issue. 4 Therefore, sex estimation is a very efficient and fast cognitive process.…”

“…6 Estimating sex from facial images has received a lot of attention over the past decade. 3 With the rapid development of technology in recent years, it has become necessary to automatically recognize people's characteristics such as gender, age, and ethnicity in computer systems. Although it is simple to estimate age and gender for humans, achieving desired outcomes with computerized vision systems is still a subject that requires further research.…”