DETECCIÓN DE IMÁGENES CON CONTENIDO EXPLÍCITO USANDO LOS MODELOS DE COLOR HSV y YCbCr

Abstract

This paper presents an investigation to explicit content images detection on mass storage devices. This work is based mainly on skin detection method; this requires the use of different techniques, as pattern recognition in the color model HSV or YCbCr. Moreover a threshold to classify pixels with some skin color tone for both color models using in this work is proposed, this to generate a classifier which can discriminate all objects within the analyzed image. The proposed system was compared with two commercial systems which carry out with the same goal as that is presented in this thesis. Finally can be probe that the proposed system be able to detect the images under study better than two 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