Adult content classification through deep convolution neural network
Adi Nurhadiyatna, Septian Cahyadi, Febri Damatraseta, Yan Rianto · 2017
Adult content filtering is one of the main challenge in Indonesia to prevent children from accessing the adult content. Conventional web blocking and filtering through domain name server filtering is not enough to prevent the adult content distribution. Mobile phones, tablet, and personal computer can distribute the adult content through the offline way. In this case, a more sophisticated and autonomous system is needed that can detect the adult content automatically. To leverage this problem, a deep neural network is used to build a model that is able to detect adult content automatically. In this experiments, our model is able to detect adult content with an accuracy of 75, 08% and 69, 02% during the validation and testing process, respectively.