Classifying objectionable websites based on image content

Wang, James; Li, Jia; Wiederhold, Gio; Firschein, Oscar

doi:10.1007/bfb0055310

Cited by 21 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An adult content detector that worked reliably to detect adult images could be a valuable tool for image search services in digital libraries [25], as well as for image categorization. The main goal of the proposed adult content detection system is to determine whether or not an input image contains an adult content by feeding the output of the skin detector to a geometric analyzer, which attempts to find human figure using geometric constraints on human figure structure.…”

Section: B Adult Image Content Detectionmentioning

confidence: 99%

Adult image content filtering: A statistical method based on Multi-Color Skin Modeling

Mofaddel¹,

Sadek²

2010

2010 2nd International Conference on Computer Technology and Development

View full text Add to dashboard Cite

Automatic skin detection is a key enabler of various imaging applications, such as face detection, human tracking, and adult content filtering. In 1996, the first paper on identifying nude pictures was published. Since then, different researchers argue different color models to be the best choice for skin detection. But, to the best our knowledge, no siguificant work has been reported previously that attempted to use more than one color model and evaluate the performance for recoguizing adult contents. In this paper, a simple statistical framework for recoguizing adult images based on an MCSM (Multi-Color Skin Model) is described. From a high level, our approach works in two steps. First, skin regions in an input image are detected using the MCSM. Then these suspected regions are fed into a specialized geometrical analyzer that attempts to assemble a human figure using simple geometric shapes derived from human body structure. Quantitative evaluation shows that our method compares favorably with the state-of-the-art methods in terms of detection rate and false alarm, while reducing the computational complexity by a factor of 1/6 with respect to the Forsyth's method.

show abstract

Section: B Adult Image Content Detectionmentioning

confidence: 99%

Adult image content filtering: A statistical method based on Multi-Color Skin Modeling

Mofaddel¹,

Sadek²

2010

2010 2nd International Conference on Computer Technology and Development

View full text Add to dashboard Cite

show abstract

“…While the work does not address PICS labels per se, it can be adapted to do so. The WIPE system [Wang et al 1998b[Wang et al 1998a, utilizing a number of image screening algorithms such as the texture analysis and a wavelet-based shape matching algorithm, analyzes patterns of an image and determines the degree of malignancy of the image. These text and image analysis results can be mapped into rating label values, which serve as the basis of Web site filtering.…”

Section: Pics and Content Labelingmentioning

confidence: 99%

Internet content filtering using isotonic separation on content category ratings

Jacob

Krishnan

Ryu

2007

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

The World Wide Web has enabled anybody with a low cost Internet connection to access vast information repositories. Some of these repositories contain information (e.g., hate speech and pornography) that is considered objectionable, especially for children to view. Several efforts-legal and technical-are underway to protect children and the generic public from accessing this type of content. We propose a technical approach utilizing a recently proposed technique called isotonic separation for filtering with content metadata if they satisfy monotone conditions. We illustrate this approach using a category rating method of PICS. In essence, we formulate the Internet content filtering problem as a classification problem on content metadata and report on experiments we conducted with the isotonic separation technique.

show abstract

“…[37] develop a MM-Classifier to classify multimedia data based on given class labels. [36] proposed IBCOW (Image-based Classification of Objectionable Websites) to classify websites into objectionable and benign websites based on image content .…”

Section: (A) Image Classificationmentioning

confidence: 99%

An Information-Driven Framework for Image Mining

Zhang

Hsu

Lee

2001

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Image mining systems that can automatically extract semantically meaningful information (knowledge) from image data are increasingly in demand. The fundamental challenge in image mining is to determine how low-level, pixel representation contained in a raw image or image sequence can be processed to identify high-level spatial objects and relationships. To meet this challenge, we propose an efficient information-driven framework for image mining. We distinguish four levels of information: the Pixel Level, the Object Level, the Semantic Concept Level, and the Pattern and Knowledge Level. High-dimensional indexing schemes and retrieval techniques are also included in the framework to support the flow of information among the levels. We believe this framework represents the first step towards capturing the different levels of information present in image data and addressing the issues and challenges of discovering useful patterns/knowledge from each level.

show abstract

Classifying objectionable websites based on image content

Cited by 21 publications

References 7 publications

Adult image content filtering: A statistical method based on Multi-Color Skin Modeling

Adult image content filtering: A statistical method based on Multi-Color Skin Modeling

Internet content filtering using isotonic separation on content category ratings

An Information-Driven Framework for Image Mining

Contact Info

Product

Resources

About