Combinatorics and image processing
Graphical Models and Image Processing
Application of Adaptive Hypergraph Model to Impulsive Noise Detection
CAIP '01 Proceedings of the 9th International Conference on Computer Analysis of Images and Patterns
Displaying Image Neighborhood Hypergraphs Line-Graphs
DGCI '02 Proceedings of the 10th International Conference on Discrete Geometry for Computer Imagery
Hi-index | 0.00 |
This paper introduces a new algorithm for visual reconstruction of digital images, which have been corrupted by mixed noise. From an image hypergraph model, we introduce a combinatorial definition of noisy data. A detection procedure is used to classify the hyperedges either as noisy or clean data. Similar to other techniques, the proposed algorithm uses then an estimation procedure to remove the effects of the noise from image data. Numerical simulations demonstrate that this algorithm suppress the effect of the noise while preserving the edges with a high degree of accuracy at a relatively low computational cost.