Abstract | ||
---|---|---|
Automatic feature detection in retinal fundus images is a fundamental issue to diagnosis eye diseases such as Glaucoma. For example, Optic Disc (OD) is a main feature for diagnosing retinal fundus diseases such as Glaucoma. This paper presents a novel algorithm for OD detection in retinal fundus images based on region growing. Image thresholding based on the entropy of the input image histogram and binary morphological operations are employed to find seed points in the region growing segmentation approach. The proposed algorithm uses an average filter to smooth input images and then, region growing is applied on the smoothed image to obtain a circular OD boundary. The performance of the proposed algorithm is evaluated on 120 high-resolution retinal fundus images of Shahid Labbafi Nedjad imaging center of Iran. The proposed method has an average sensitivity/speciflcity of 98.6%/97.2% and it is computationally efficient in the presence of high-resolution images. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/BMEI.2015.7401481 | 2015 8th International Conference on Biomedical Engineering and Informatics (BMEI) |
Keywords | Field | DocType |
Glaucoma,optic disc Detection,image thresholding,retinal fundus images,region growing | Computer vision,Histogram,Pattern recognition,Computer science,Binary image,Fundus (eye),Optic disc,Image segmentation,Region growing,Artificial intelligence,Thresholding,Image histogram | Conference |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sara Omid | 1 | 0 | 0.34 |
Jamshid Shanbehzadeh | 2 | 253 | 15.43 |
Zeinab Ghassabi | 3 | 40 | 3.13 |
S. Shervin Ostadzadeh | 4 | 14 | 2.96 |