A novel scheme for intelligent recognition of pornographic images

Computing and Communications

Keywords

Computer Science - Computer Vision and Pattern Recognition

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

A novel scheme for intelligent recognition of pornographic images. / Kia, Seyed Mostafa; Rahmani, Hossein; Mortezaei, Reza et al.
In: arxiv.org, 01.02.2014.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Kia, SM, Rahmani, H, Mortezaei, R, Ebrahimi Moghaddam, M & Namazi, A 2014, 'A novel scheme for intelligent recognition of pornographic images', arxiv.org. <http://adsabs.harvard.edu/abs/2014arXiv1402.5792K>

APA

Kia, S. M., Rahmani, H., Mortezaei, R., Ebrahimi Moghaddam, M., & Namazi, A. (2014). A novel scheme for intelligent recognition of pornographic images. arxiv.org. http://adsabs.harvard.edu/abs/2014arXiv1402.5792K

Vancouver

Kia SM, Rahmani H, Mortezaei R, Ebrahimi Moghaddam M, Namazi A. A novel scheme for intelligent recognition of pornographic images. arxiv.org. 2014 Feb 1.

Author

Kia, Seyed Mostafa ; Rahmani, Hossein ; Mortezaei, Reza et al. / A novel scheme for intelligent recognition of pornographic images. In: arxiv.org. 2014.

Bibtex

@article{8ac959909c014ae0b7aa61601704c071,

title = "A novel scheme for intelligent recognition of pornographic images",

abstract = "Harmful contents are rising in internet day by day and this motivates the essence of more research in fast and reliable obscene and immoral material filtering. Pornographic image recognition is an important component in each filtering system. In this paper, a new approach for detecting pornographic images is introduced. In this approach, two new features are suggested. These two features in combination with other simple traditional features provide decent difference between porn and non-porn images. In addition, we applied fuzzy integral based information fusion to combine MLP (Multi-Layer Perceptron) and NF (Neuro-Fuzzy) outputs. To test the proposed method, performance of system was evaluated over 18354 download images from internet. The attained precision was 93% in TP and 8% in FP on training dataset, and 87% and 5.5% on test dataset. Achieved results verify the performance of proposed system versus other related works.",

keywords = "Computer Science - Computer Vision and Pattern Recognition",

author = "Kia, {Seyed Mostafa} and Hossein Rahmani and Reza Mortezaei and {Ebrahimi Moghaddam}, Mohsen and Amer Namazi",

year = "2014",

month = feb,

day = "1",

language = "English",

journal = "arxiv.org",

}

RIS

TY - JOUR

T1 - A novel scheme for intelligent recognition of pornographic images

AU - Kia, Seyed Mostafa

AU - Rahmani, Hossein

AU - Mortezaei, Reza

AU - Ebrahimi Moghaddam, Mohsen

AU - Namazi, Amer

PY - 2014/2/1

Y1 - 2014/2/1

N2 - Harmful contents are rising in internet day by day and this motivates the essence of more research in fast and reliable obscene and immoral material filtering. Pornographic image recognition is an important component in each filtering system. In this paper, a new approach for detecting pornographic images is introduced. In this approach, two new features are suggested. These two features in combination with other simple traditional features provide decent difference between porn and non-porn images. In addition, we applied fuzzy integral based information fusion to combine MLP (Multi-Layer Perceptron) and NF (Neuro-Fuzzy) outputs. To test the proposed method, performance of system was evaluated over 18354 download images from internet. The attained precision was 93% in TP and 8% in FP on training dataset, and 87% and 5.5% on test dataset. Achieved results verify the performance of proposed system versus other related works.

AB - Harmful contents are rising in internet day by day and this motivates the essence of more research in fast and reliable obscene and immoral material filtering. Pornographic image recognition is an important component in each filtering system. In this paper, a new approach for detecting pornographic images is introduced. In this approach, two new features are suggested. These two features in combination with other simple traditional features provide decent difference between porn and non-porn images. In addition, we applied fuzzy integral based information fusion to combine MLP (Multi-Layer Perceptron) and NF (Neuro-Fuzzy) outputs. To test the proposed method, performance of system was evaluated over 18354 download images from internet. The attained precision was 93% in TP and 8% in FP on training dataset, and 87% and 5.5% on test dataset. Achieved results verify the performance of proposed system versus other related works.

KW - Computer Science - Computer Vision and Pattern Recognition

M3 - Journal article

JO - arxiv.org

JF - arxiv.org

ER -

Research

Links

Keywords