Publication: Autenticación de imágenes digitales mediante patrones locales de texturas
Loading...
Official URL
Full text at PDC
Publication Date
2018
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Exportar
Abstract
La autenticidad de una imagen digital sufre graves amenazas debido a la existencia de poderosas herramientas para la edición de imágenes digitales que facilitan la modificación del contenido de las mismas sin dejar huellas visibles de tales cambios. Este problema unido a la facilidad de distribución de la información a través de plataformas digitales como blogs, Internet o redes sociales, ha provocado que la sociedad tienda a aceptar como cierto todo lo que ve sin cuestionar su veracidad. En este trabajo se propone un método de autenticación de imágenes digitales mediante el análisis de patrones locales de textura. El sistema propuesto combina el patrón binario local con la transformada discreta wavelet y la transformada discreta del coseno para extraer las características de cada uno de los bloques de la imagen investigada. Posteriormente, se utiliza la máquina de soporte vectorial para crear el modelo que permita la verificación de la autenticidad de una imagen. Para la evaluación del método propuesto se realizaron experimentos con bases de datos públicas de imágenes falsificadas que son ampliamente utilizadas en la literatura.
The authenticity of a digital image suffers serious threats due to the existence of powerful digital image editing tools that make easier the modification of the contents of the image without leaving visible traces of such changes. This problem, joined with the ease of distribution of information through digital platforms such as blogs, the Internet or social networks, has caused society to tend to accept as true all that it sees without questioning its truthfulness. This work proposes a method of authentication of digital images through the analysis of local texture patterns. The proposed system combines the local binary pattern with the discrete wavelet transform and the discrete cosine transform to extract the characteristics of each blocks of the investigated image. Subsequently, the vector support machine is used to create the model that allows verification of the authenticity of an image. For the evaluation of the proposed method experiments were carried out with public databases of tampered images that are widely used in the literature.
The authenticity of a digital image suffers serious threats due to the existence of powerful digital image editing tools that make easier the modification of the contents of the image without leaving visible traces of such changes. This problem, joined with the ease of distribution of information through digital platforms such as blogs, the Internet or social networks, has caused society to tend to accept as true all that it sees without questioning its truthfulness. This work proposes a method of authentication of digital images through the analysis of local texture patterns. The proposed system combines the local binary pattern with the discrete wavelet transform and the discrete cosine transform to extract the characteristics of each blocks of the investigated image. Subsequently, the vector support machine is used to create the model that allows verification of the authenticity of an image. For the evaluation of the proposed method experiments were carried out with public databases of tampered images that are widely used in the literature.
Description
Universidad Complutense, Facultad de Informática, curso 2016/2017