Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features

P. Kuppusamy; Mehfooza Munavar Basha; Che Lun Hung

doi:10.1109/ICSTSN53084.2022.9761339

Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features

P. Kuppusamy, Mehfooza Munavar Basha, Che Lun Hung

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

Recent developments in machine learning increases the researcher's interest in processing the medical images in diagnosis. The medical field requires precise diagnosis to detect the disease. This paper proposed a fusion of features that are extracted from canny edge detector and Gabor feature extractors. These features dimension is huge while combining the features of canny edge detector and Gabor extractor. The Principal Component Analysis applied on the extracted features to reduce the dimension to increase the computational speed. The ensemble method Random Forest is applied on the features to classify the vessel's existence in fundus image. The results have been compared with Decision Tree algorithm. The experiments have proved the Random Forest performed better result with 99.86% accuracy and F1 score 0.997.

Original language	English
Title of host publication	1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665421119
DOIs	https://doi.org/10.1109/ICSTSN53084.2022.9761339
State	Published - 2022
Externally published	Yes
Event	1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022 - Villupuram, India Duration: 25 03 2022 → 26 03 2022

Publication series

Name	1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022

Conference

Conference	1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022
Country/Territory	India
City	Villupuram
Period	25/03/22 → 26/03/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Gabor filter
blood vessel segmentation
canny edge
decision tree
random forest
retinal vessels

Access to Document

10.1109/ICSTSN53084.2022.9761339

Cite this

Kuppusamy, P., Basha, M. M., & Hung, C. L. (2022). Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features. In 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022 (1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSTSN53084.2022.9761339

Kuppusamy, P. ; Basha, Mehfooza Munavar ; Hung, Che Lun. / Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features. 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022).

@inproceedings{ec69a6904208448d906faefb3f45ad39,

title = "Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features",

abstract = "Recent developments in machine learning increases the researcher's interest in processing the medical images in diagnosis. The medical field requires precise diagnosis to detect the disease. This paper proposed a fusion of features that are extracted from canny edge detector and Gabor feature extractors. These features dimension is huge while combining the features of canny edge detector and Gabor extractor. The Principal Component Analysis applied on the extracted features to reduce the dimension to increase the computational speed. The ensemble method Random Forest is applied on the features to classify the vessel's existence in fundus image. The results have been compared with Decision Tree algorithm. The experiments have proved the Random Forest performed better result with 99.86% accuracy and F1 score 0.997.",

keywords = "Gabor filter, blood vessel segmentation, canny edge, decision tree, random forest, retinal vessels",

author = "P. Kuppusamy and Basha, {Mehfooza Munavar} and Hung, {Che Lun}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022 ; Conference date: 25-03-2022 Through 26-03-2022",

year = "2022",

doi = "10.1109/ICSTSN53084.2022.9761339",

language = "英语",

series = "1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022",

address = "美国",

}

Kuppusamy, P, Basha, MM & Hung, CL 2022, Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features. in 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022. 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022, Institute of Electrical and Electronics Engineers Inc., 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022, Villupuram, India, 25/03/22. https://doi.org/10.1109/ICSTSN53084.2022.9761339

Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features. / Kuppusamy, P.; Basha, Mehfooza Munavar; Hung, Che Lun.
1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features

AU - Kuppusamy, P.

AU - Basha, Mehfooza Munavar

AU - Hung, Che Lun

PY - 2022

Y1 - 2022

N2 - Recent developments in machine learning increases the researcher's interest in processing the medical images in diagnosis. The medical field requires precise diagnosis to detect the disease. This paper proposed a fusion of features that are extracted from canny edge detector and Gabor feature extractors. These features dimension is huge while combining the features of canny edge detector and Gabor extractor. The Principal Component Analysis applied on the extracted features to reduce the dimension to increase the computational speed. The ensemble method Random Forest is applied on the features to classify the vessel's existence in fundus image. The results have been compared with Decision Tree algorithm. The experiments have proved the Random Forest performed better result with 99.86% accuracy and F1 score 0.997.

AB - Recent developments in machine learning increases the researcher's interest in processing the medical images in diagnosis. The medical field requires precise diagnosis to detect the disease. This paper proposed a fusion of features that are extracted from canny edge detector and Gabor feature extractors. These features dimension is huge while combining the features of canny edge detector and Gabor extractor. The Principal Component Analysis applied on the extracted features to reduce the dimension to increase the computational speed. The ensemble method Random Forest is applied on the features to classify the vessel's existence in fundus image. The results have been compared with Decision Tree algorithm. The experiments have proved the Random Forest performed better result with 99.86% accuracy and F1 score 0.997.

KW - Gabor filter

KW - blood vessel segmentation

KW - canny edge

KW - decision tree

KW - random forest

KW - retinal vessels

UR - http://www.scopus.com/inward/record.url?scp=85130047786&partnerID=8YFLogxK

U2 - 10.1109/ICSTSN53084.2022.9761339

DO - 10.1109/ICSTSN53084.2022.9761339

M3 - 会议稿件

AN - SCOPUS:85130047786

T3 - 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022

BT - 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022

Y2 - 25 March 2022 through 26 March 2022

ER -

Kuppusamy P, Basha MM, Hung CL. Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features. In 1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (1st IEEE International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2022). doi: 10.1109/ICSTSN53084.2022.9761339

Retinal Blood Vessel Segmentation using Random Forest with Gabor and Canny Edge Features

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this