Histogram of Oriented Gradients (HOG)-Based Artificial Neural Network (ANN) Classifier for Glaucoma Detection

Histogram of Oriented Gradients (HOG)-Based Artificial Neural Network (ANN) Classifier for Glaucoma Detection

Law Kumar Singh, Pooja, Hitendra Garg, Munish Khanna
Copyright: © 2022 |Pages: 32
DOI: 10.4018/IJSIR.309940
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Glaucoma is a severe condition of the optic nerve resulting in the loss of eyesight. The proposed methodology has introduced the extraction of HOG (histogram of oriented gradients) features from the retinal fundus image. After the removal of HOG features, the authors compare the performance of five different machine learning techniques like k-nearest neighbour (KNN), support vector machine (SVM), linear discriminant analysis (LDA), naïve bayes, and artificial neural network. The process of image classification is based on analyzing the numerical properties of the obtained image features and classifying the data into different categories. In the paper, the authors intend to classify whether the image belongs to the glaucomatous category or the healthy category. After the application of the different classification algorithms to the test data and further analysis of the results, they could conclude that the SVM classifier provided an accuracy of 90%, KNN 86%, Naïve Bayes 96%, LDA 86%, and ANN 96.90% on the dataset in hand.
Article Preview
Top

2. Literature Survey

For this section, we have shortlisted some of the prominent prior studies published in this domain, and we have discussed their major contribution as below.

For the support for the automatic detection of diseases (Claro et. al., 2016), the application of digital image processing (DIP) methodology is important in medicinal scenarios. Therefore, the authors aimed to explore a methodology that would grant us automatic detection of glaucoma. Firstly, the required database is acquired, next optic disc segmentation is performed, after that texture features are extracted in different colour models, and finally classification is performed, which helps us differentiate between glaucomatous and nonglaucomatous eyes. The proposed method gave an accuracy of 93%.

(Ahmad et. al., 2014) in their paper focuses on the methodology of processing an image for the recognition of glaucoma that specifically hinders the (OD) optic disc. The hindrance is caused due to enhancements in the dimensions of the cup. Glaucoma was classified based on the features that were being extricated from fundus images of the retina. Cup to Disc Ratio (CDR) and Neuroretinal Rim Ratio in (ISNT quadrants) are two of the features involved.The technique gave an accuracy of 97.5% when being performed on 80 retinal images, and the process on an average took a processing time of about 0.8141 seconds.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 3 Issues (2023)
Volume 13: 4 Issues (2022)
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing