Private Body Part Detection using Deep Learning

Tabone, André; Bonnici, Alexandra; Cristina, Stefania; Farrugia, Reuben A.; Camilleri, Kenneth P.

doi:10.5220/0009101502050211

Cited by 6 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The object classes to be detected were based on what explicit content each source generates to obtain a total of eight classes. It was noted that "Female Genitalia" should be split into two subsidiary classes since the appearance differs considerably between instances of posing and instances of sexual activity [29]. Since eight out of our nine classes are essentially body parts, they are expected to share a number of features.…”

Section: Sexual Objectsmentioning

confidence: 98%

“…Their MIL approach achieved a better accuracy when compared with traditional pornographic classification methods such as image retrieval or bag-of-features. Tabone et al 2020 [29] propose a two step ConvNet system that uses a binary MobileNet classifier as an initial pornography detector. A windowing approach combined with a multi-class MobileNet classifier then locates the five main sexual body parts: male genitalia, female genitalia, buttocks and sex toys.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The three additional categories include cartoons and drawings depicting children engaged in sexual activity, benign exploitation of children, and adult pornography. The current array of deep learning tools aimed at the detection of pornographic content [11,19,29,31] are limited to flagging sensitive content and do not distinguish between different degrees of pornographic material. Thus, LEAs do not have the means to automatically categorise and organise the sensitive content seized from the perpetrators.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pornographic content classification using deep-learning

Tabone

Camilleri

Bonnici

et al. 2021

Proceedings of the 21st ACM Symposium on Document Engineering

Self Cite

View full text Add to dashboard Cite

Controlling the distribution of sensitive content such as pornography has become paramount with the ever-growing accessibility to the internet. Manual filtering of such large volumes of data is practically impossible, thus, the automatic detection of said material is sought after by Law Enforcement Agencies (LEAs) and has been tackled in various manners. However, the sorting of flagged pornographic documents is still done manually using scales that describe hierarchical degrees of content severity. In this paper, we address pornography detection by creating a model capable of locating and labelling sexual organs in images and extend this model to perform image classification to provide the user with one of 19 semantically meaningful descriptors of the content. Generating these descriptors serves as a proof of concept before approaching LEAs to work with illegal CSA material and scales such as COPINE. After creating our own custom sexual organ object detection dataset for the task at hand, we achieved an object detection mean average precision score of 63.63% and a top-3 classification accuracy of 87.78%. CCS CONCEPTS• Computing methodologies → Object detection.

show abstract

Section: Sexual Objectsmentioning

confidence: 98%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pornographic content classification using deep-learning

Tabone

Camilleri

Bonnici

et al. 2021

Proceedings of the 21st ACM Symposium on Document Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…As part of the model development, they trained a colour-saliency preserved mixture deformable part model on the colour attributes and histogram-of-oriented gradient features, which reflect the shape and colour distributions of sexual objects in different poses. Tabone [13] proposed a classification system with seven sexual objects: buttocks, female breasts, female genitals (divided into two sub-classes: female genital posing and female genital active), male genitals, sex toys, and non-porn images. Eventually, they annotated these classes with five-set labelled points: one center point and four perpendicular offset points.…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%

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

2022

IJIES

View full text Add to dashboard Cite

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.

show abstract

“…However, the selection of appropriate pornographic organs or objects as well as the method of annotating depended heavily on the study scale and perspective. Noticeably, Tabone et al [14] proposed seven sexual organs and objects for pornography classification included buttocks, female breast, female genital (which are divided into two sub-classes: female genital posing and female genital active), male genital, sex toy and benign object. Eventually, they annotated those classes with a five-set labeled point: one center point and four perpendicularly offset for each.…”

Section: Related Workmentioning

confidence: 99%

A Novel Pornographic Visual Content Classifier based on Sensitive Object Detection

Phan¹,

Nguyen²,

Nguyen³

et al. 2021

IJACSA

View full text Add to dashboard Cite

With the increasing amount of pornography being uploaded on the Internet today, arises the need to detect and block such pornographic websites, especially in Eastern cultural countries. Studying pornographic images and videos, show that explicit sensitive objects are typically one of the main characteristics portraying the unique aspect of pornography content. This paper proposed a classification method on pornographic visual content, which involved detecting sensitive objects using object detection algorithms. Initially, an object detection model is used to identify sensitive objects on visual content. The detection results are then used as high-level features combined with two other high-level features including skin body and human presence information. These high-level features finally are fed into a fusion Support Vector Machine (SVM) model, thus draw the eventual decision. Based on 800 videos from the NDPI-800 dataset and the 50.000 manually collected images, the evaluation results show that our proposed approach achieved 94.06% and 94.88% in Accuracy respectively, which can be compared with the cutting-edge pornographic classification methods. In addition, a pornographic alerting and blocking extension is developed for Google Chrome to prove the proposed architecture's effectiveness and capability. Working with 200 websites, the extension achieved an outstanding result, which is 99.50% Accuracy in classification.

show abstract

Private Body Part Detection using Deep Learning

Cited by 6 publications

References 0 publications

Pornographic content classification using deep-learning

Pornographic content classification using deep-learning

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

A Novel Pornographic Visual Content Classifier based on Sensitive Object Detection

Contact Info

Product

Resources

About