Fast Localization of the Optic Disc Using Projection of Image Features

Abstract

Optic Disc (OD) localization is an important pre-processing step that significantly simplifies subsequent segmentation of the OD and other retinal structures. Current OD localization techniques suffer from impractically-high computation times (few minutes per image). In this work, we present a fast technique that requires less than a second to localize the OD. The technique is based upon obtaining two projections of certain image features that encode the x- and y- coordinates of the OD. The resulting 1-D projections are then searched to determine the location of the OD. This avoids searching the 2-D image space and, thus, enhances the speed of the OD localization process. Image features such as retinal vessels orientation and the OD brightness are used in the current method. Four publicly-available databases, including STARE and DRIVE, are used to evaluate the proposed technique. The OD was successfully located in 330 images out of 340 images (97%) with an average computation time of 0.65 s.

Computational efficiency of optic disk detection on fundus image: a survey

“…Youssif et al [11] used the directional pattern of retinal blood vessels for the OD detection. Mahfouz et al [3] combined three characteristics which are the disk brightness, the vessel convergence and the vascular direction. In the work of Hashim et al [4], a binary mask is applied on the intensity channel to exclude the background pixels.…”

“…The blood vessel is generally assumed to be no wider than 15 pixels [4], with a thickness of 15% of the OD diameter [3]. The ratio of OD diameter to the thickness of the main vessels is approximately equal to [6].According the D OD relationship and assigning the ratio to 6.5, the thickness is calculated with the following relation:…”

“…The mainly objectives are the extractionof retina and retinal components, theenhancement of image contrast [7,4,3,1], orthe denoising [5]. It can be seen in Table 3 that all preprocessing have complexity between n² and 28.n².…”

“…Other methods proceed to extract candidate list of OD locations. Thereafter, the OD location is performed by computing parameter for each candidate such as MSE orientation error [6], scoring index [3], etc., and hence locating OD. This principle leads to improve the robustness of their techniques with respect to the eventual lesions.…”

Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review

“…The algorithm had higher failure rate on diseased images with white lesions. Mahfouz et al [44] used the horizontal and vertical edge maps to locate the ONH center. These maps can be used to accurately localize the ONH center based upon a simple observation that the central retinal artery and vein emerge from the ONH mainly in the vertical direction and then progressively branch into the main horizontal vessels.…”