Please use this identifier to cite or link to this item:
http://localhost:8080/xmlui/handle/123456789/3211
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Khan, Mubashir | - |
dc.contributor.author | Khan, Sahil Jafar [16DCO58] | - |
dc.contributor.author | Ansari, Mohd. Akram Sajid Ahmed [16DCO47] | - |
dc.contributor.author | Shaikh, Mohd. Yusuf Abdul Salam [16DCO76] | - |
dc.date.accessioned | 2019-08-01T12:02:26Z | - |
dc.date.available | 2019-08-01T12:02:26Z | - |
dc.date.issued | 2019-05 | - |
dc.identifier.uri | http://www.aiktcdspace.org:8080/jspui/handle/123456789/3211 | - |
dc.description.abstract | Traditional Retinal Scans Provides color image of the scan due to which the visibility of the identification eye diseases.Thus in an effort to improve the visibility of scans we presenet our paper making use Neural Networks to get better visibility. The field of Ophthalmology has increasingly turned into medical imaging to play important role in diagnosing diseases. It requires retinal scanned images in identifi- cation of eye diseases. Determining eye disease on the basis of traditional retinal scans can sometimes be difficult due to presence of hemorrhage or thin blood vessels since the image is not very clear. Therefore this paper attempts to improve the quality of retinal scans through im- age segmentation and supervised machine learning algorithms so diagnosis can be as accurate as possible. Keywords: Neural Networks,Opthalmology,Image Segmentation,GAN’s(Generative Adversarial Network. | en_US |
dc.language.iso | en | en_US |
dc.publisher | AIKTC | en_US |
dc.relation.ispartofseries | PE0589; | - |
dc.subject | Project Report - CO | en_US |
dc.title | Detection of retinal blood vessel using deep learning | en_US |
dc.type | Project Report | en_US |
Appears in Collections: | Computer Engineering - Project Reports |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
PE0589.pdf | 2.38 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.