Violence Detection in Images Using Deep Neural Networks
Edwin-Mark Grigore · 2020
Software and technology has evolved and expanded so much over the last decades, that is present in everybody's life in every little aspect, and more and more significantly at children's disposal.Starting from this reality, it is necessary the identification of the images that contain scenes of violence or emotionally disturbing scenes, images that contain blood or depict human bodies with open wounds, violent fires, or presence of guns and weapons.Machine learning (ML) is capable of extracting features from images and learn to identify the images that depict inappropriate scenes for children, using different techniques.With the recent advances in deep learning, traditional ML methods, such as Support Vector Machines, have been surpassed by deep neural networks that are also employed by our solution for violence detection.