Name
Abstract | ||
|---|---|---|
We propose a novel vessel enhancement filter for retinal images. The filter can be used as a preprocessing step in applications such as vessel segmentation/visualization, and pathology detection. The proposed filter combines the eigenvalues of the Hessian matrix, the response of matched filters, and edge constraints on multiple scales. The eigenvectors of the Hessian matrix provide the orientation of vessels and so only one matched filter is necessary at each pixel in a given scale. This makes the proposed filter more efficient compared with existing multiscale matched filters. Edge constraints are used to suppress the response of spurious boundary edges. Experimental evaluation on the publicly available DRIVE dataset demonstrate improved performance of the proposed filter compared with known techniques. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ISBI.2007.356924 | ISBI |
Keywords | Field | DocType |
eye,hessian matrices,vessel segmentation,matched filters,med- ical imaging,retinal vessel segmentation,retina l images,index terms— vessel enhancement,hybrid filtering,blood vessels,retinal images,image segmentation,eigenvectors,vessel enhancement filter,eigenvalues and eigenfunctions,hes- sian directions,edge constraints,medical image processing,hessian matrix,optical filters,indexing terms,filtering,matched filter,pathology,gray scale,pixel | Computer vision,Scale-space segmentation,Pattern recognition,Visualization,Computer science,Hessian matrix,Filter (signal processing),Image segmentation,Preprocessor,Artificial intelligence,Pixel,Matched filter | Conference |
ISSN | ISBN | Citations |
1945-7928 | 1-4244-0672-2 | 6 |
PageRank | References | Authors |
0.55 | 16 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Changhua Wu | 1 | 189 | 16.89 |
| Gady Agam | 2 | 391 | 43.99 |
| Peter Stanchev | 3 | 35 | 7.40 |