Klasifikasi Kelompok Usia Melalui Citra Wajah Berbasis Image Texture Analysis pada Sistem Automatic Video Filtering

Abstract

Nowadays information technology makes it easier for everyone to access various information, this easiness harms minors, because it is possible to access adult content from the internet, television or mobile devices. The problem is the unavailability of the system for filtering and authentication to get information by the face. The face contains information related to personal characteristics such as age, etc. feature extraction is an important stage in the face recognition process. This study proposed local binary pattern (LBP) and gray level co-occurrence matrix (GLCM) as feature extraction to describe face feature, and we use artificial neural network to classify the human age, the experiment result after calculation with confusion matrix obtained average acceleration of 94.8%, precision of 93.7% and recall of 92.3%, it’s performance measure obtained proposed method can be described face feature it well, so that, the proposed method can be used as reference material to development video filtering system by age of the users in access information based on video especially pornography and violence content.