For Project Enquiry +91 9791 044 044

EXISTING SYSTEM

PROPOSED SYSTEM

EXISTING CONCEPT:

          This system classifies separately the vessels detected in each quadrant, and finally it combines the results.

          Tracking strategy based on a minimal path approach is applied to join the vessel segments located at different radii in order to support the classification by voting.

PROPOSED CONCEPT:       

          We mostly focus on a characteristic of the retinal vessel tree that, at least in the region near the optic disc, veins rarely cross veins and arteries rarely cross arteries.

          We may define different types of intersection points: bifurcation, crossing, meeting, and connecting points.

EXISTING ALGORITHM:

          Colour based Clustering Algorithm

PROPOSED ALGORITHM:

          Automatic Graph Generation Algorithm          

ALGORITHM DEFINITION:

          The clustering approach divides the retinal image into four quadrants.

ALGORITHM DEFINITION:

          The graph extracted from the segmented retinal Vasculature is analyzed to decide on the type of intersection points (graph nodes), and afterwards one of two labels is assigned to each vessel segment (graph links).

DRAWBACKS:

          The classification is propagated outside this zone, where little or no information is available to discriminate arteries from veins.

          Low accuracy.

ADVANTAGES:

          Arteries and veins information extracted from a graph which represents the vascular network.

          High accuracy.