A Mid-level Video Representation based on Binary Descriptors: A Case Study for Pornography Detection

TL;DR

This paper introduces a novel binary descriptor-based method for pornography detection in videos, utilizing BossaNova and mid-level representations to improve accuracy and reduce computational complexity compared to existing approaches.

Contribution

It proposes a new local binary feature extraction method combined with BossaNova representation and mid-level video descriptors, enhancing detection accuracy and efficiency.

Findings

Achieved 92.40% accuracy in pornography detection.

Reduced classification error by 16% over state-of-the-art methods.

Provided effective video description techniques using BNVD and BoW-VD.

Abstract

With the growing amount of inappropriate content on the Internet, such as pornography, arises the need to detect and filter such material. The reason for this is given by the fact that such content is often prohibited in certain environments (e.g., schools and workplaces) or for certain publics (e.g., children). In recent years, many works have been mainly focused on detecting pornographic images and videos based on visual content, particularly on the detection of skin color. Although these approaches provide good results, they generally have the disadvantage of a high false positive rate since not all images with large areas of skin exposure are necessarily pornographic images, such as people wearing swimsuits or images related to sports. Local feature based approaches with Bag-of-Words models (BoW) have been successfully applied to visual recognition tasks in the context of pornography detection. Even though existing methods provide promising results, they use local feature descriptors that require a high computational processing time yielding high-dimensional vectors. In this work, we propose an approach for pornography detection based on local binary feature extraction and BossaNova image representation, a BoW model extension that preserves more richly the visual information. Moreover, we propose two approaches for video description based on the combination of mid-level representations namely BossaNova Video Descriptor (BNVD) and BoW Video Descriptor (BoW-VD). The proposed techniques are promising, achieving an accuracy of 92.40%, thus reducing the classification error by 16% over the current state-of-the-art local features approach on the Pornography dataset.