Classified optic disc localization algorithm based on verification model. (February 2018)

• Record Type: Journal Article
• Authors: Zou, Beiji; Chen, Changlong; Zhu, Chengzhang; Duan, Xuanchu; Chen, Zailiang
• Is Part Of: Computers & graphics. Volume 70(2018)
• Page Start: 281
• Page End: 287
• Publication Date: 2018-02
• Subjects: Optic disc -- Classified localization -- Verification model -- Vessels segmentation; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2017.07.031
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: We propose a framework to integrate two OD localization methods. A verification model is presented according to the OD features. The model is mainly to check whether the candidate region contains the real OD. The classification algorithm is realized by verifying the OD candidate region. Proposed method can easily combine with other highly-accurate algorithms. Graphical abstract: Abstract: Optic disc (OD) localization plays an important role in the automatic screening of ocular fundus diseases. However, it is still a challenge at present to balance the accuracy and efficiency of the OD localization for various of retinal fundus images. In this paper, we propose a new framework to integrate two classes methods based on image intensity and vascular information to obtain the OD location. The classification algorithm within the framework is based on a verification model. Firstly, an OD candidate region is obtained by image intensity. Secondly, the candidate region is validated by verification model. If the verification is passed, the corresponding position of the region is determined as the OD center. Otherwise, the OD is located by the parabola fitting of the main blood vessels and the relocation. The proposed method was evaluated on four public databases STARE, DRIVE, DIARETDB0 and DIARETDB1, and the accuracy rate was 96.3%, 100%, 100% and 100%, respectively. The running time is 0.05 s, 0.03 s, 0.13 s and 0.12 s per image through the validation in each database, while the time spent on images failed in verification is about 0.49 s, 0.38 s, 2.21 s and 2.15 s, individually.