LSPD: A Large-Scale Pornographic Dataset for Detection and Classification

Abstract

This paper introduces a new dataset named Large-Scale Pornographic Dataset for detection and classification (LSPD) that intends to advance the standard quality of pornographic visual content classification and sexual object detection tasks. As we recognize, the LSPD dataset is the first ever dataset for both object detection and image/video classification tasks in this area. The dataset gathers a large-scale corpus of pornographic/nonpornographic images and videos containing a rich diversity of context. The images and videos are not only labelled with their representative class but are also annotated by polygon masks of four private sexual objects (breasts, male and female genitals, and anuses). Our dataset contains 500,000 images and 4,000 videos, with more than 50,000 annotated images. To ensure fair use of the dataset, we present a detailed statistical analysis and provide baseline benchmarking scenarios for both image/video classification and instance detection/segmentation tasks. Finally, we evaluate the performance of four object detection algorithms and a Convolutional Neural Network (CNN) classifier on these scenarios.