Novel method for pornographic image detection using HSV and YCbCr color models

• Published in: Revista Facultad de Ingeniería no. 64; pp. 79 - 90
• Main Authors: Marcial Basilio, Jorge A., Aguilar Torres, Gualberto, Sánchez Pérez, Gabriel, Toscano Medina, Karina, Pérez Meana, Héctor M.
• Format: Journal Article
• Language: English
• Published: Universidad de Antioquia 03.10.2012
• Subjects: computer forensics; explicit content; pattern recognition; skin detection; the HSV and YCbCr color models
• ISSN: 0120-6230; 2422-2844
• DOI: 10.17533/udea.redin.13117

In this paper a novel method to explicit content or pornographic images detection is proposed, using the transformation from RGB to HSV or YCbCr color model, which is the most usual format to images that exists on Internet, moreover the using of a threshold to skin detection applying the color models HSV and YCbCr is proposed. Using the proposed threshold the image is segmented, once the image segmented, the skin quantity localized in that image is calculated. The obtained results using the proposed system are compared with two programs which carry out with the same goal, the Forensic Toolkit 3.1 Explicit Image Detection (FTK 3.1 EID) and the Parabenís Porn Detection Stick that are two the most commercials solutions to pornographic images detection. The reported results in this paper were obtained using three sets of images, each one of them consist of 800 images choosing randomly which 400 are natural images and the rest are explicit content images, this sets were used to probe the proposed system and the two tools commercials. The proposed system achieved a 78,75% of recognizing, 28% of false positives and 14,50% of false negatives, the software FTK 3.1 Explicit Image Detection obtained 72,12% of recognizing, 38,50% of false positives and 17,25% of false negatives. Parabenís Porn Detection Stick achieved 74,25% of recognizing with 16% of false positives and 35,50% of false negatives. Finally can be prove that the proposed system be able to detect the images under study better than two of the software solutions more using for forensic researchers, for this reason the proposed method can be applied to computer forensics or in detection of pornographic images stored on mass storage devices.