Abstract | ||
---|---|---|
Extreme learning machine (ELM) is an effective machine learning technique that widely used in image processing. In this paper, a new supervised method for segmenting blood vessels in retinal images is proposed based on the ELM classifier. The proposed algorithm first constructs a 7-D feature vector using multi-scale Gabor filter, Hessian matrix and bottomhat transformation. Then, an ELM classifier is trained on gold standard examples of vessel segmentation images to classify previous unseen images. The algorithm was tested on the publicly available DRIVE database - a digital image database for vessel extraction. Experimental results on both real-captured images and public database images demonstrate that our method shows comparative performance against other methods, which make the proposed algorithm a suitable tool for automated retinal image analysis. |
Year | DOI | Venue |
---|---|---|
2017 | 10.20965/jaciii.2017.p1280 | JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS |
Keywords | Field | DocType |
retinal image,vessel segmentation,Extreme Learning Machine (ELM),Gabor filter,Hessian matrix,bottom-hat transformation | Computer vision,Vessel segmentation,Pattern recognition,Computer science,Extreme learning machine,Hessian matrix,Gabor filter,Retinal image,Artificial intelligence,Retinal,Machine learning | Journal |
Volume | Issue | ISSN |
21 | 7 | 1343-0130 |
Citations | PageRank | References |
0 | 0.34 | 28 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fan Guo | 1 | 12 | 5.25 |
Da Xiang | 2 | 0 | 0.34 |
Beiji Zou | 3 | 231 | 41.61 |
chengzhang zhu | 4 | 15 | 3.91 |
Shengnan Wang | 5 | 0 | 0.34 |