Skripsi

DETEKSI EKSUDAT PADA CITRA RETINA MENGGUNAKAN MEAN SHIFT SEGMENTATION DAN ADAPTIVE THRESHOLDING

---

Penilaian

---

Diabetic retinopathy is the retinal damage of people with diabetes mellitus. Diabetic retinopathy suffer can vision to decline until the suffer is blind for a long time. Diabetes disease is characterized by the appearance of several disorders. Abnormalities that accur in the retina one of which is describe by exudate. Exudate is the main sign of diabetic retinopathy caused by leakage and dilation of blood vessels around the retina. Exudate in the form of dots or spots that have a yellowish color with various shapes and fairly high contrast. In this final project research the authors conducted the exudate detection study using Mean Shift Segmentation and Adaptive Thresholding to diagnose diseases of the retina. In thir study the authors used the STARE dataset. The first convert the original image into a RGB to Luv, eliminate fine lines in the image by using mean shift segmentation. after that the image will be converted to grayscale. Then, it will be converted into a green channel. Then, the image will be detected in the exudate candidate area using illumination correction. Enhance the contrast of retinal images with contrast adjustments. Next, removal of the optical disk. After remove the optic disk the detection of exudate is done by segmentation using adaptive thresholding. then the removal of small objects that can interfere with exudate detection. Then, to remove small holes and to refine the contour morphology closing is used. Next, use ROI to remove the outline on the retina. Using this method, getting the average result for accuracy of 97.87% and spesificity of 96.71%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2007000890	T33654	T336542020	Central Library (REFERENSI)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T336542020

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer., 2020

Collation

xi, 63 hlm.; ilus., tab: 28 cm

Language

Indonesia

ISBN/ISSN

-

Classification

003.07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem komputer
Ilmu Komputer
Mean Shift Segmentation

Specific Detail Info

-

Statement of Responsibility

EM

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment