Retinal Blood Vessel Segmentation on Style-augmented Images
The average human lifespan increased dramatically in the second half of 20th century. It was mainly due to technological improvements, which were driven by the continuous war preparations, and while humans have got another 20 years to live, unfortunately there are some sad side effects added to the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Babes-Bolyai University, Cluj-Napoca
2021-07-01
|
| Series: | Studia Universitatis Babes-Bolyai: Series Informatica |
| Subjects: | |
| Online Access: | http://193.231.18.162/index.php/subbinformatica/article/view/1174 |
| _version_ | 1797322205083729920 |
|---|---|
| author | Marcell Dávid TÓTH Attila KISS |
| author_facet | Marcell Dávid TÓTH Attila KISS |
| author_sort | Marcell Dávid TÓTH |
| collection | DOAJ |
| description |
The average human lifespan increased dramatically in the second half of 20th century. It was mainly due to technological improvements, which were driven by the continuous war preparations, and while humans have got another 20 years to live, unfortunately there are some sad side effects added to the elderly life. Various diseases can attack the eye, our major organ responsible for receiving information, therefore many researches were devoted to examine these diseases, their early signs, and how could they be stopped. From the start of 21th century, methods aided by computer were more and more involved in these processes, up to the current trend of using Convolutional Neural Networks (CNNs). While supervised methods, CNNs do achieve accuracy which can be compared to a skilled ophtalmologist, they require a tremendous amount of labeled data which is sparse in medical fields because the amount of time and resources needed to create them. One natural solution is to augment the data present, that is, copying the distribution while adding a small variety, like coloring an image differently. That is, what our paper aims to explore, whether a texturing algorithm, the Neural Style Transfery can be used to make a data set richer, and therefore helping a classifier CNN to achieve better results.
Received by the editors: 4 December 2020.
2010 Mathematics Subject Classification. 68U10, 68T01, 92B20.
1998 CR Categories and Descriptors. I.4.6 [I.2 Image Processing and Computer Vision]: Segmentation - Region, partitioning; I.5.1 [Pattern Recognition]: Models – Neural Nets.
|
| first_indexed | 2024-03-08T05:10:50Z |
| format | Article |
| id | doaj.art-152a02e8f3e746f7bf7bdd77e1f8e5cf |
| institution | Directory Open Access Journal |
| issn | 2065-9601 |
| language | English |
| last_indexed | 2024-03-08T05:10:50Z |
| publishDate | 2021-07-01 |
| publisher | Babes-Bolyai University, Cluj-Napoca |
| record_format | Article |
| series | Studia Universitatis Babes-Bolyai: Series Informatica |
| spelling | doaj.art-152a02e8f3e746f7bf7bdd77e1f8e5cf2024-02-07T10:03:34ZengBabes-Bolyai University, Cluj-NapocaStudia Universitatis Babes-Bolyai: Series Informatica2065-96012021-07-0166110.24193/subbi.2021.1.05Retinal Blood Vessel Segmentation on Style-augmented ImagesMarcell Dávid TÓTH0Attila KISS1ELTE Eötvös Loránd University, Budapest, Hungary, Email address: p3kxga@inf.elte.huJ. Selye University, Komárno, Slovakia Email address: kissae@ujs.sk The average human lifespan increased dramatically in the second half of 20th century. It was mainly due to technological improvements, which were driven by the continuous war preparations, and while humans have got another 20 years to live, unfortunately there are some sad side effects added to the elderly life. Various diseases can attack the eye, our major organ responsible for receiving information, therefore many researches were devoted to examine these diseases, their early signs, and how could they be stopped. From the start of 21th century, methods aided by computer were more and more involved in these processes, up to the current trend of using Convolutional Neural Networks (CNNs). While supervised methods, CNNs do achieve accuracy which can be compared to a skilled ophtalmologist, they require a tremendous amount of labeled data which is sparse in medical fields because the amount of time and resources needed to create them. One natural solution is to augment the data present, that is, copying the distribution while adding a small variety, like coloring an image differently. That is, what our paper aims to explore, whether a texturing algorithm, the Neural Style Transfery can be used to make a data set richer, and therefore helping a classifier CNN to achieve better results. Received by the editors: 4 December 2020. 2010 Mathematics Subject Classification. 68U10, 68T01, 92B20. 1998 CR Categories and Descriptors. I.4.6 [I.2 Image Processing and Computer Vision]: Segmentation - Region, partitioning; I.5.1 [Pattern Recognition]: Models – Neural Nets. http://193.231.18.162/index.php/subbinformatica/article/view/1174Medical Image Processing, Retinal Blood Vessel Segmentation, Neural Style Transfer. |
| spellingShingle | Marcell Dávid TÓTH Attila KISS Retinal Blood Vessel Segmentation on Style-augmented Images Studia Universitatis Babes-Bolyai: Series Informatica Medical Image Processing, Retinal Blood Vessel Segmentation, Neural Style Transfer. |
| title | Retinal Blood Vessel Segmentation on Style-augmented Images |
| title_full | Retinal Blood Vessel Segmentation on Style-augmented Images |
| title_fullStr | Retinal Blood Vessel Segmentation on Style-augmented Images |
| title_full_unstemmed | Retinal Blood Vessel Segmentation on Style-augmented Images |
| title_short | Retinal Blood Vessel Segmentation on Style-augmented Images |
| title_sort | retinal blood vessel segmentation on style augmented images |
| topic | Medical Image Processing, Retinal Blood Vessel Segmentation, Neural Style Transfer. |
| url | http://193.231.18.162/index.php/subbinformatica/article/view/1174 |
| work_keys_str_mv | AT marcelldavidtoth retinalbloodvesselsegmentationonstyleaugmentedimages AT attilakiss retinalbloodvesselsegmentationonstyleaugmentedimages |