Filtros no lineales para reducir ruido en imágenes a color
Fuente:
Redalyc
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo científico |
| Lenguaje: | es |
| Publicado: |
Universidad de Carabobo
2017
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1876442033794580480 |
|---|---|
| author | Hyxia Latouche |
| author_facet | Hyxia Latouche |
| contents | Filtros no lineales para reducir ruido en imágenes a color Hyxia Latouche Kelvin Solarte Joan Ordoñez Luis Sánchez Ingeniería luminance noise reduction Nonlinear filters images processing The present investigation consisted in the implementation Montecarlo Sequential methods to restore, in real time, color images altered by Gaussian noise. Were specifically implemented the algorithms of Divided Di ff erence Filter, Adaptive Central Di ff erence and Cubature Kalman Filter. The method of filtering only the luminance of the image by transforming RGB to YIQ is used in order to reduce the computation time. For the restoration of the images, a filtering process is proposed by making two paths, one horizontal and one vertical in the matrix of the Y layer. The resulting filtered layers were averaged in order to obtain a better estimation of the values for each pixel after filtration. The results showed that the implemented filters perform a significant noise reduction compared to the original image. The e ffi ciency of the filters was evaluated in terms of the mean absolute error (EAM) and the peak signal-to-noise ratio (PSNR) of the estimated states, showing little variation among the calculated errors. Finally, related with the execution time of algorithms, a significant di ff erence was found between the filters, being the Divided Di ff erence filter the most e ffi cient. 2017 artículo científico 1316-6832 https://www.redalyc.org/articulo.oa?id=70753474006 es http://www.redalyc.org/revista.oa?id=707 Revista INGENIERÍA UC application/pdf Universidad de Carabobo Revista INGENIERÍA UC (República Bolivariana de Venezuela) Num.2 Vol.24 |
| format | Artículo científico |
| id | redalyc_70753474006 |
| institution | Redalyc |
| language | es |
| publishDate | 2017 |
| publisher | Universidad de Carabobo |
| spellingShingle | Filtros no lineales para reducir ruido en imágenes a color Hyxia Latouche Ingeniería luminance noise reduction Nonlinear filters images processing Filtros no lineales para reducir ruido en imágenes a color Hyxia Latouche Kelvin Solarte Joan Ordoñez Luis Sánchez Ingeniería luminance noise reduction Nonlinear filters images processing The present investigation consisted in the implementation Montecarlo Sequential methods to restore, in real time, color images altered by Gaussian noise. Were specifically implemented the algorithms of Divided Di ff erence Filter, Adaptive Central Di ff erence and Cubature Kalman Filter. The method of filtering only the luminance of the image by transforming RGB to YIQ is used in order to reduce the computation time. For the restoration of the images, a filtering process is proposed by making two paths, one horizontal and one vertical in the matrix of the Y layer. The resulting filtered layers were averaged in order to obtain a better estimation of the values for each pixel after filtration. The results showed that the implemented filters perform a significant noise reduction compared to the original image. The e ffi ciency of the filters was evaluated in terms of the mean absolute error (EAM) and the peak signal-to-noise ratio (PSNR) of the estimated states, showing little variation among the calculated errors. Finally, related with the execution time of algorithms, a significant di ff erence was found between the filters, being the Divided Di ff erence filter the most e ffi cient. 2017 artículo científico 1316-6832 https://www.redalyc.org/articulo.oa?id=70753474006 es http://www.redalyc.org/revista.oa?id=707 Revista INGENIERÍA UC application/pdf Universidad de Carabobo Revista INGENIERÍA UC (República Bolivariana de Venezuela) Num.2 Vol.24 |
| title | Filtros no lineales para reducir ruido en imágenes a color |
| topic | Ingeniería luminance noise reduction Nonlinear filters images processing |
| url | https://www.redalyc.org/articulo.oa?id=70753474006 |