A Machine Learning Based Adult Content Detection Using Support Vector Machine
Ganesh Gajula, Ajinkya Hundiwale, Shreyas Mujumdar, L.R. Saritha · 2020
In the era of internet, recognizing pornographic images is of great significance for protecting children's physical and mental health. With small kids surfing over the internet they are just one click away from getting access to pornographic images. However, this task is very challenging as the key pornographic contents (example. breast, private part) in an image often lie in local regions of small size. The proposed model is based on supervised learning-based Support Vector Machine (SVM) algorithm which returns whether an image is safe or unsafe. The proposed model not only differentiates the image between safe/unsafe but also blurs/colors the exposed skin portion completely black if the image is found to be unsafe (i.e. pornographic image) using image processing technique. So, that the end user won't be able to see exposed private parts in an image. When tested on our newly-collected large scale dataset demonstrates the effectiveness of the proposed method, achieving an accuracy of ~91 % when tested 4k pornographic images and 4k normal images.