Explicit Content Detection System: An Approach towards a Safe and Ethical Environment

• Main Authors: Ali Qamar Bhatti, Muhammad Umer, Syed Hasan Adil, Mansoor Ebrahim, Daniyal Nawaz, Faizan Ahmed
• Format: Article
• Language: English
• Published: Hindawi Limited 2018-01-01
• Series: Applied Computational Intelligence and Soft Computing
• Online Access: http://dx.doi.org/10.1155/2018/1463546

An explicit content detection (ECD) system to detect Not Suitable For Work (NSFW) media (i.e., image/ video) content is proposed. The proposed ECD system is based on residual network (i.e., deep learning model) which returns a probability to indicate the explicitness in media content. The value is further compared with a defined threshold to decide whether the content is explicit or nonexplicit. The proposed system not only differentiates between explicit/nonexplicit contents but also indicates the degree of explicitness in any media content, i.e., high, medium, or low. In addition, the system also identifies the media files with tampered extension and label them as suspicious. The experimental result shows that the proposed model provides an accuracy of ~ 95% when tested on our image and video datasets.