Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
Image Zooming Model Based on Image Decomposition
verfasst von : Yongguo Zheng, Songhe Gao
Erschienen in: Transactions on Edutainment XIV
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
According to the different morphological characteristics between cartoons and textures in images, an image zooming model was proposed which based on image decomposition. The model decomposed the image into cartoons and textures by decomposition model; it analyzed the features of isotropic model and anisotropic model, the cartoon part was zoomed by isotropic model and the texture part was zoomed by anisotropic model. The using of shock filter eliminated the weak edge due to image zooming. At last, it achieved the amplification by combining the two zoomed parts. Simulation experiment results showed the model was good enough to zoom the image, strengthen the edge and guarantee the smoothness of the image. The model had better visual effects and the value of Peak Signal-to-Noise Ratio (PSNR) and Root-mean-square error (RMSE) was better than Bi-cubic and anisotropic model.