Abstract | ||
---|---|---|
A novel method of active contours with shape prior knowledge is presented in this research in order to improve its robustness for partially occluded objects. Our prior is based on a free-registration shape template estimation by using a complete and stable set of invariant descriptors. The prior template is then incorporated into the level set model, using a stopping function that updates the evolving curve only in the region of variability between the active contour and the researched template so that the computation time is reduced considerably. The proposed framework is demonstrated using both simulated and real data involving the segmentation of occluded and noisy images. Results show better robustness and stability compared to the well-known methods using statistics. |
Year | DOI | Venue |
---|---|---|
2019 | 10.23919/EUSIPCO.2019.8902638 | 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO) |
Keywords | Field | DocType |
Invariant descriptors, active contour, free registration | Active contour model,Pattern recognition,Segmentation,Computer science,Level set,Robustness (computer science),Independent set,Invariant (mathematics),Artificial intelligence,Computation | Conference |
ISSN | Citations | PageRank |
2076-1465 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ines Sakly | 1 | 0 | 1.01 |
Mohamed Amine Mezghich | 2 | 0 | 0.34 |
Slim M'hiri | 3 | 0 | 0.34 |
Faouzi Ghorbel | 4 | 361 | 46.48 |