Proceedings of the 10th International Conference on Computer Modeling and Simulation 2018

DOI: 10.1145/3177457.3177484

|View full text |Cite

|

Sign up to set email alerts

|

Methods of Pornography Detection

Sasan Karamizadeh

¹

,

Abouzar Arabsorkhi

²

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction2

Related Work 21 Pornography Detection Approach1

Related Work1

Trabalhos Relacionados1

Citation Types

Supporting

0

Mentioning

8

Contrasting

0

Unclassified

2

Year Published

2019

2019

2022

2022

Publication Types

Select...

Article5

Other3

Book1

Relationship

Self Cite0

Independent9

Authors

Journals

Cited by 14 publications

(10 citation statements)

References 38 publications

Supporting

0

Mentioning

8

Contrasting

0

Unclassified

2

Order By: Relevance

“…The recognition and classification pornographic content have been a classic problem solved by various approaches and methods. Karamizadeh and arabsorkhi [7] divided porn-identification methods into six main categories: colour-based, shape-based, local and global feature-based, bag-of-words for filtering images, and deep learning methods. Alternatively, we recognize four main approaches to porn-identification: skin-based, handcrafted featurebased, deep learning-based, and sensitive-object based.…”

Section: Related Work 21 Pornography Detection Approachmentioning

confidence: 99%

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

2022

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.

“…The recognition and classification pornographic content have been a classic problem solved by various approaches and methods. Karamizadeh and arabsorkhi [7] divided porn-identification methods into six main categories: colour-based, shape-based, local and global feature-based, bag-of-words for filtering images, and deep learning methods. Alternatively, we recognize four main approaches to porn-identification: skin-based, handcrafted featurebased, deep learning-based, and sensitive-object based.…”

Section: Related Work 21 Pornography Detection Approachmentioning

confidence: 99%

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

2022

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.

“…Numerous researchers have employed neural networks to achieve significant enhancements in image recognition and classification [35]- [37]. Recently, many researchers have employed neural network-based approaches to recognize pornography [38], [39]. Moustafa et al [13] were the first to employ neural networks for the detection of pornographic images and video by combining AlexNet [33] and GoogleNet [40].…”

Section: Related Workmentioning

confidence: 99%

A Pornographic Images Recognition Model based on Deep One-Class Classification With Visual Attention Mechanism

¹

,

²

,

³

et al. 2020

View full text Add to dashboard Cite

The existing approaches usually treat the recognition of pornographic images as a binary or multi-class classification task, which is realized by extracting a variety of features. However, these approaches ignore the problem of infinite kinds in the negative samples and lose sight of the impact of uncertainty in classification tasks, resulting in inadequate negative data sets and incorrect recognition of samples that are not in the training set. In order to address this challenge, this paper proposes a method named Deep One-Class with Attention for Pornography (DOCAPorn) that recognizes the pornographic images through the one-class classification model based on neural networks and introduces the visual attention mechanism to enhance the performance of recognition. Moreover, since the existing approaches based on deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image, the geometric distortion caused by image scaling is not considerd in the existing approaches, which reduces the pornographic image recognizition accuracy. In order to solve this issue, this paper proposes the Scale Constraint Pooling (SCP) that converts the inputs of different dimensions into outputs of the same dimension. In addition, all the existing approaches ignore the adversarial attacks in the field of pornographic image recognition. In order to deal with this problem, the paper proposes the Preprocessing for Compressing and Reconstructing (PreCR), a pre-processing approach that reduces the subtle perturbation through compressing the images and then reconstructs the purified image for recognition. The proposed approach is verified by conducting comparative experiments using custom datasets. The experimental results showed that we achieved an accuracy of 98.419% on our dataset. In addition, the proposed approach yielded a recognition accuracy of 95.632% on the NPDI dataset. Furthermore, the obtained results demonstrate that the proposed approach not only effectively recognizes pornographic images but also effectively defends the adversarial attacks.

“…Ademais, verifica-se a existência de vários métodos para a classificação de imagens, entre eles, para a classificação de imagem pornográfica [Karamizadeh e Arabsorkhi 2018] Desta forma, foram apresentados trabalhos que visam a detecção de imagem PI, modificação e visualização de imagens e aquele que se baseia no algoritmo NB para a detecção de imagem PI. Verificou-se que o uso de CNN para a detecção de imagem PI tem sido feito com frequência nos trabalhos atuais, ainda que os resultados apresentados por estes são aceitáveis.…”

Section: Trabalhos Relacionadosunclassified

Mitigando os Efeitos de GAN em Classificação de Imagens com CNN

et al. 2019

Anais Do XIX Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais (SBSeg 2019)

View full text Add to dashboard Cite

A CNN (Convolutional Neural Network) tem sido frequentemente usada para solução de problemas, gerando um modelo que pode prever a classe da imagem. Neste trabalho, a ausência de integridade na CNN é verificada usando uma GAN (Generative Adversarial Network). Para isso, modelamos um classificador de autenticidade baseado no algoritmo NB (Naive Bayes). Quando os modelos NB e CNN propostos trabalham juntos, 88,88% de acerto foram alcançados. Em 89,88% dos casos as imagens fakes foram identificadas e descartadas. No caso específico da CNN, obteve-se uma precisão de 85,06% com uma confiança de 95%.

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Product

Browser Extension Assistant by scite Citation Statement Search Reference Check Visualizations Dashboards Explore Journals Explore Organizations Explore Funders Embedding Badge Embedding Citation Search Pricing

Resources

Blog Help & FAQ Accessibility Statement API Terms For Universities & Governments For Researchers For Publishers For Corporate, Pharma & Enterprise Author Marketing Become an Affiliate Get an organization trial or quote scite Data & Services

About

News & Press Careers Read our Paper Coverage

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Copyright © 2024 scite LLC. All rights reserved.

Made with 💙 for researchers

Part of the Research Solutions Family.