DocumentCode :
2993444
Title :
Fast and Effectively Identify Pornographic Images
Author :
Fu, Yanjun ; Wang, Weiqiang
Author_Institution :
Sch. of Inf. Sci. & Eng., Grad. Univ. of Chinese Acad. of Sci., Beijing, China
fYear :
2011
fDate :
3-4 Dec. 2011
Firstpage :
1122
Lastpage :
1126
Abstract :
In this paper, we present a practical solution to identifying pornographic images based on multiple low-level image features and support vector machine (SVM). First, the region of interest (ROI) is obtained from an original image based on the detection of skin-like pixels in YCbCr color space. The ROI is then classified into being acceptable or unacceptable by its size. Images without ROIs or acceptable ROIs are deemed to be benign images. For images with acceptable ROI, the color, texture and shape features are further extracted on ROI, and then fed to a SVM classifier to perform the task of recognition. Our approach has obtained 96.05% sensitivity and 96.17% specificity on a dataset containing 8,000 pornographic images and 12,500 benign images, as well as the processing speed of about 0.026 seconds for a PC to determine whether a given image with an average size of 420 by 433 pixels is pornographic.
Keywords :
feature extraction; image classification; image colour analysis; image texture; support vector machines; SVM classifier; YCbCr color space; color feature extraction; multiple low-level image features; pornographic image identification; region of interest; shape feature extraction; skin-like pixel detection; support vector machine; texture feature extraction; Feature extraction; Image color analysis; Image recognition; Shape; Skin; Support vector machines; Vectors; SVM; co-occurrence matrix; moment; pornographic image; region of interest;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Security (CIS), 2011 Seventh International Conference on
Conference_Location :
Hainan
Print_ISBN :
978-1-4577-2008-6
Type :
conf
DOI :
10.1109/CIS.2011.249
Filename :
6128433
Link To Document :
بازگشت