159 Hits in 5.9 sec

Patch-based skin color detection and its application to pornography image filtering

Haiqiang Zuo, Weiming Hu, Ou Wu
2010 Proceedings of the 19th international conference on World wide web - WWW '10  
In this paper, we propose two patch-based skin color detection algorithms: regular patch and irregular patch skin color detection algorithms.  ...  Detecting human skin tone is of utmost importance in pornography image filtering algorithms.  ...  PATCH-BASED SKIN COLOR DETECTION We first convert the original image from RGB color space to orthogonal YCbCr color space.  ... 
doi:10.1145/1772690.1772887 dblp:conf/www/ZuoHW10 fatcat:z2kc2qb4m5gr5ppumrgc25ths4

A mid-level video representation based on binary descriptors: A case study for pornography detection

Carlos Caetano, Sandra Avila, William Robson Schwartz, Silvio Jamil F. Guimarães, Arnaldo de A. Araújo
2016 Neurocomputing  
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.  ...  With the growing amount of inappropriate content on the Internet, such as pornography, arises the need to detect and filter such material.  ...  The authors are thankful to CNPq, CAPES and FAPEMIG, Brazilian research and development agencies for the support to this work.  ... 
doi:10.1016/j.neucom.2016.03.099 fatcat:rhnk6ab6xbdmlgkhi7paod36mi


2013 Journal of Computer Science  
Obscenity detection from images and videos are now crucial due to social and ethical reasons. It has been two decades the research on this field started.  ...  Most of the works are based on skin color detection, which are not suitable for finding obscenity.  ...  HLE201104220082A) and National Natural Science Foundation of China (grant no. 61105133) and Shenzhen Public Technical Platform (grant no. CXC201005260003A).  ... 
doi:10.3844/jcssp.2013.1715.1721 fatcat:qp5rn2up4rexlort53zfjjcxly

Illicit Image Detection: An MRF Model Based Stochastic Approach [chapter]

Mofakharul Islam, Paul Watters, John Yearwood, Mazher Hussain, Lubaba A. Swarna
2012 Lecture Notes in Electrical Engineering  
In this paper, we propose a stochastic model based novel approach to investigate and implement a pornography detection technique towards a framework for automated detection of pornography based on contextual  ...  The steady growth of the Internet, sophisticated digital image processing technology, the cheap availability of storage devices and surfer's ever-increasing interest on images have been contributing to  ...  stuff on images and thus failing to utilize its full potential in areas like detection of pornography.  ... 
doi:10.1007/978-1-4614-3535-8_40 fatcat:iirvkzb5b5ewvlbca6ndt7ezqm

Illicit Image Filtering and Classification Techniques

Dr. D. M. Bhalerao, Anita Parihar
2015 International Journal of Engineering Research and  
Even though different systems for this application were offered in the past, which are based on simple skin color features and have quite poor performance.  ...  We present a method to classify images into different categories of pornographic content to create a system for filtering illicit images from network traffic.  ...  ACKNOWLEGMENT I wish to express my genuine thanks and deep sense of gratitude to respected guide Dr. D M.  ... 
doi:10.17577/ijertv4is041037 fatcat:gdhbdee65nelzfy3ekdd6z5ilq

Illicit Image Detection Using Erotic Pose Estimation Based on Kinematic Constraints [chapter]

Mofakharul Islam, Paul Watters, John Yearwood, Mazher Hussain, Lubaba A. Swarna
2012 Lecture Notes in Electrical Engineering  
In this paper, we propose a novel approach to investigate and implement a pornography detection technique towards a framework for automated detection of pornography based on most commonly found erotic  ...  The detection of pornography remains an important and significant research problem, since there is great potential to minimize harm to the community.  ...  In fact, all the pornography detection approaches are based on skin detection module that defines a decision rule based on which skin and non-skin pixels will be discriminated.  ... 
doi:10.1007/978-1-4614-3535-8_41 fatcat:q7wdcp4g75eala6tk7ydj4xhn4


2006 International Journal of Image and Graphics  
Based on skin color detection results, shape features are extracted and fed into a boosted classifier to decide whether or not the skin regions represent a nude.  ...  This paper reports an investigation on adult images detection based on the shape features of skin regions.  ...  skin patches and adult images.  ... 
doi:10.1142/s0219467806002082 fatcat:yt4g66beazg3rg2qgxcaevk3yu

Constructing Pornographic Images Detector based on naïve Bayesian classifier

Alaa Taqa, Bayez AL-Sulaifanie
2010 Journal of education and science  
Skin and non-skin color models are constructed and exploited by constructing a Bayesian decision rule based skin detector.  ...  It achieves a detective rate of (91.48%) with (6.67%) false positive rate. ٨٦ This research is organized as follows: sections 2 explains the skin detection, and segmentation.  ...  The detection of skin regions in color images is a preliminary step in several application, such as face detection and pornographic images detection [8] [4] .  ... 
doi:10.33899/edusj.2010.57978 fatcat:ijrwyebgw5gifgha4zcpxzttzm

An offline parallel architecture for forensic multimedia classification

Luca Spalazzi, Marina Paolanti, Emanuele Frontoni
2021 Multimedia tools and applications  
limited hardware resources and it is built on an open-source software to limit its costs.  ...  As a case study, we focus on the identification of child pornography images.  ...  In [33] , the authors have proposed a model based on skin detection which filters pornographic image. It merely detects static images which rely on a certain threshold.  ... 
doi:10.1007/s11042-021-10819-x fatcat:ussp2xk4gvfmji2wzhofivs2yu

A Study on Low Resolution Androgenic Hair Patterns for Criminal and Victim Identification

Han Su, Adams Wai Kin Kong
2014 IEEE Transactions on Information Forensics and Security  
Skin mark patterns and blood vessel patterns are recently proposed to address this problem. However, they are invisible in low resolution images and dense androgenic hair can cover them completely.  ...  Identifying criminals and victims in images (e.g., child pornography and masked gunmen) can be a challenging task, especially when neither their faces nor tattoos are observable.  ...  images in the last experiment.  ... 
doi:10.1109/tifs.2014.2306591 fatcat:zjmliw3idfas5ottwae2v7pgcu

Content-Based Filtering for Video Sharing Social Networks [article]

Eduardo Valle, Sandra de Avila, Antonio da Luz Jr., Fillipe de Souza, Marcelo Coelho, Arnaldo Araújo
2011 arXiv   pre-print
We evaluate our method in three social network applications, related to the detection of unwanted content - pornographic videos, violent videos, and videos posted to artificially manipulate popularity  ...  In this paper we compare the use of several features in the task of content filtering for video social networks, a very challenging task, not only because the unwanted content is related to very high-level  ...  is based on color or texture-based skin detection [].  ... 
arXiv:1101.2427v1 fatcat:brr2rvfxbjfixcvqohhv674pw4


M. A. Chyad, H. A. Alsattar, B. B. Zaidan, A. A. Zaidan, Ghailan A. Al Shafeey
2019 IEEE Access  
An extensive search is conducted to identify articles that deal with skin detection, skin segmentation, skin tone detector, and skin recognition issues, related techniques are reviewed comprehensively  ...  Furthermore, state-of-the-art is a step to demonstrate the novelty of the presented study by conducted a statistical analysis for previous studies such as (Dataset, Color spaces, features, image type,  ...  The algorithm for the proposed approach is based on a novel stochastic model that detects and identifies patches of child pornography on images.  ... 
doi:10.1109/access.2019.2924989 fatcat:viwgq5we4ra4va3pxa4q4hy3vm

A Bag-Of-Features Approach Based On Hue-Sift Descriptor For Nude Detection

Arnaldo Araujo, Sandra Avila, Ana Lopes, Rodrigo Oliveira, Anderson Peixoto
2009 Zenodo  
The authors are grateful to CNPq, CAPES and FAPEMIG, Brazilian research funding agencies, for the financial support to this work.  ...  To detect pornographic images, [20] proposed a skin model based on the combination of YIQ, YUV, and HSV color models. A white balance algorithm is applied to better detection of skin areas.  ...  The first step of the system proposed in [10] is to use content-based image retrieval to determine whether the image contains humans in it. This retrieval step is based on color and shape features.  ... 
doi:10.5281/zenodo.41583 fatcat:x6dmomm7fvddxdxgy3rjml2upu

Pornography Detection Using Bossanova Video Descriptor

Arnaldo Araujo, Sandra Avila, Carlos Caetano, Silvio Guimarães
2014 Zenodo  
The authors are thankful to CNPq, CAPES and FAPEMIG, Brazilian research and development agencies, and the INCT InWeb, for the support to this work.  ...  [8, 9] developed a BoW-based approach, which used the HueSIFT, a SIFT variant including color information, to classify images and videos.  ...  Moreover, the majority of those works is based on the detection of human skin [3] [4] [5] [6] .  ... 
doi:10.5281/zenodo.44114 fatcat:l7zxxept4rfixlwvda3o6opvsu

Pornographic Image Recognition via Weighted Multiple Instance Learning [article]

Jin Xin, Wang Yuhui, Tan Xiaoyang
2019 arXiv   pre-print
In this paper, we model each image as a bag of regions, and follow a multiple instance learning (MIL) approach to train a generic region-based recognition model.  ...  and 100K normal images.  ...  To detect skin-like pixels, the input image is typically transformed from the RGB model to the RCbCr color space, and a pixel is considered to be skin-like when it satisfies a few linear constraints in  ... 
arXiv:1902.03771v1 fatcat:x6almdzggrgepl3lsulepe6mcu
« Previous Showing results 1 — 15 out of 159 results