Automatic Segmentation of Retinal Images by Using Morphological Watershed and Region Growing Method (original) (raw)
Retinal image segmentation is essential for diagnosing various problems occurs in eye. Retinal image segment is one of the critical issues because these images contain very small nerves and some artifacts present in it. This paper proposes an automatic morphological watershed segmentation and region growing method to change the representation of an image into something that is more meaningful and easier to analyze the interested object. There are several methods that intend to perform segmentation, but it is difficult to adapt easily and detect the very small nerves accurately. To resolve this problem, this paper aims to present an adaptable automatic morphological watershed segmentation and region growing method that can be applied to any type of retinal images which is exactly diagnosed even with the small changes that occur in the image. This proposed method is based in a model of morph function which applies the morphological watershed operator to a gray scale image. Morphological segment technique is used to segment the image and selecting the specific image objects, thinning the object to found the root nerves. After using a morphological watershed operation to expose the basic elements within an image, it is often useful to extract and analyze specific information about those image elements. The region growing segmentation performs region growing for a given image region within the array that are connected to neighboring region pixels and that fall within provided constraints[7].
Sign up for access to the world's latest research.
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.