Retinal Blood Vessel Segmentation Using PCA

• Author(s): K. Balaji ; T. Vineela ; K. Surya Vamsi ; P. Ravi Kiran ; P. Siddarth Keshav Raj
• Paper ID: 1702809
• Page: 34-39
• Published Date: 05-07-2021
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 5 Issue 1 July-2021

Abstract

The morphology of blood vessels in retinal fundus images is an important indicator of diseases like glaucoma, hypertension and diabetic retinopathy. The accuracy of retinal blood vessels segmentation affects the quality of retinal image analysis which is used in diagnosis methods in modern ophthalmology. In this project we are segmenting those retinal blood vessels of fundus images which helps the diagnosis of the eye related diseases. Through this blood vessel segmentation, the side effects caused due to the diagnosis of eye for different eye diseases can be reduced. In this project, we are performing the segmentation process by using PCA method. This paper proposes a three step thresholding based process to extract the blood vessels from the retinal fundus images. In the first step a unique combination of principal component analysis (PCA) and adaptive histogram equalization is used to enhance the retinal images. In the second step the blood vessels from the retinal fundus images are extracted by using the thresholding method. In the last step the morphological method is used to remove the unwanted pixels and the output segmented image is converted into a color image. In this paper we are using a DRIVE dataset to measure the performance of the proposed method. Our proposed method achieves an accuracy of 0.964, sensitivity about 0.624 and specificity about 0.991.

Keywords

Blood vessel, fundus image, histogram equalization, morphological method, PCA

Citations

IRE Journals:
K. Balaji , T. Vineela , K. Surya Vamsi , P. Ravi Kiran , P. Siddarth Keshav Raj "Retinal Blood Vessel Segmentation Using PCA" Iconic Research And Engineering Journals Volume 5 Issue 1 2021 Page 34-39

IEEE:
K. Balaji , T. Vineela , K. Surya Vamsi , P. Ravi Kiran , P. Siddarth Keshav Raj "Retinal Blood Vessel Segmentation Using PCA" Iconic Research And Engineering Journals, 5(1)