Abstract | ||
---|---|---|
Optic disc (OD) segmentation is an important step in analyzing the color fundus image. Most existing approaches are based on the shape prior and visual appearance of the OD boundary. However, the current ways of integrating the shape and appearance are simple. We argue that the performance of OD segmentation can be improved by better shape-appearance modeling. In this paper, we propose to learn a sequence of supervised descent directions between the coordinates of OD boundary and their surrounding visual appearances for OD segmentation. In addition, we introduce the histograms of gradient orientations to represent the OD appearance. Experimental results on six datasets clearly show that the proposed method improves the OD segmentation and outperforms the state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.neucom.2017.08.033 | Neurocomputing |
Keywords | Field | DocType |
Optic disc segmentation,Supervised descent method | Computer vision,Histogram,Scale-space segmentation,Pattern recognition,Segmentation,Optic disc,Artificial intelligence,Mathematics,Fundus image,Visual appearance | Journal |
Volume | Issue | ISSN |
275 | C | 0925-2312 |
Citations | PageRank | References |
1 | 0.36 | 24 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Annan Li | 1 | 222 | 14.22 |
Zhiheng Niu | 2 | 52 | 3.50 |
Jun Cheng | 3 | 214 | 20.65 |
Fengshou Yin | 4 | 125 | 9.66 |
Damon Wing Kee Wong | 5 | 434 | 37.78 |
Shuicheng Yan | 6 | 162 | 10.26 |
Shuicheng Yan | 7 | 9701 | 359.54 |