Image-based pornography detection

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

Proceedings of the 2008 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2008

First Page

627

Last Page

631

Publication Date

12-1-2008

Abstract

This paper presents an algorithm for detecting pornography or nudity in color images based on a skin color distribution model. The skin color model is based on correlation analyses of RGB and HSV color components. This model is used to identify and locate skin regions in an image. The skin regions are analyzed for clues indicating nudity or non-nudity such as their sizes and relative distances from each other. The Nudity Detection Algorithm is able to detect nudity with a 94.85% recall and a false positive rate of 6.52% on a set of images consisting of 641 nude images and 936 non-nude images.

html

Disciplines

Computer Sciences

Keywords

Nudity; Pornography; Imaging systems; Color vision; Human skin color

Upload File

wf_no

This document is currently not available here.

Share

COinS