An Evaluation of State-of-the-Art Object Detectors for Pornography Detection

Sui Lyn Hor, Hezerul Abdul Karim, Mohd Haris Lye Abdullah, Nouar AlDahoul, Sarina Mansor, Mohammad Faizal Ahmad Fauzi, John See, Abdulaziz Saleh Ba Wazir

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Pornographic and nudity content detection in videos is gaining importance as Internet grows to become a source for exposure to such content. Recent literature involved pornography recognition using deep learning techniques such as convolutional neural network, object detection models and recurrent neural networks, as well as combinations of these methods. In this paper, the effectiveness of three pretrained object detection models (YOLOv3, EfficientDet-d7x and Faster R-CNN with ResNet50 as backbone) were tested to compare their performance in detecting pornographic contents. Video frames consisting of real humans from the public NPDI dataset were utilised to form four categories of target content (female breast, female lower body, male lower body and nude human) by cropping the specific image regions and augmenting them. Results demonstrated that COCO-pretrained EfficientDet-d7x model achieved the highest overall detection accuracy of 75.61%. Interestingly, human detection of YOLOv3 may be dependent on image quality and/or presence of external body parts that belong only to humans.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)
PublisherIEEE
ISBN (Electronic)9781665435925
DOIs
Publication statusPublished - 20 Oct 2021
Event7th IEEE International Conference on Signal and Image Processing Applications 2021 - Virtual, Online, Malaysia
Duration: 13 Sep 202115 Sep 2021
https://sps.ieeemy.org/icsipa2021/

Conference

Conference7th IEEE International Conference on Signal and Image Processing Applications 2021
Abbreviated titleICSIPA 2021
Country/TerritoryMalaysia
CityVirtual, Online
Period13/09/2115/09/21
Internet address

Keywords

  • deep learning
  • nudity detection
  • object detection
  • pornography detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics

Fingerprint

Dive into the research topics of 'An Evaluation of State-of-the-Art Object Detectors for Pornography Detection'. Together they form a unique fingerprint.

Cite this