Hybrid feature vector based detection of Glaucoma

• Published in: Multimedia tools and applications Vol. 78; no. 24; pp. 34247 - 34276
• Main Authors: Krishnamoorthi, Nirmala, Chinnababu, Vinoth Kumar
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2019; Springer Nature B.V
• Subjects: Algorithms; Classification; Classifiers; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Feature extraction; Glaucoma; Histograms; Image analysis; Image contrast; Image detection; Image enhancement; Image processing; Image segmentation; Morphology; Multimedia Information Systems; Regression analysis; Retinal images; Sensitivity analysis; Special Purpose and Application-Based Systems; Support vector machines; Glaucoma; Histogram of oriented gradient; Local binary pattern; Logistic regression; Naive Bayes; Fractal features; Support vector machine
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-019-08249-x

This paper focus on the investigation of the potential in retinal image analysis for the detection of Glaucoma. The computer-based analysis of the parameter involves the use of image processing algorithms for pre-processing, localization and segmentation of the region of interest (ROI), feature extraction from ROI, and classification. The initial step in computer based detection system includes the enhancing scheme for improving the contrast of the fundus image from the three databases, Drishti-GS1, FAU and RIMONE. The optic disc region has been localized from the enhanced image. Structural deformation of the optic disc region, one of the primary indicators of the glaucoma demands more accuracy in segmentation process. As a solution to this problem, non-morphological features are extracted from the enhanced optic disc region. The non-morphological features from spatial domain include Local Binary Pattern, Histogram of Oriented Gradient and Fractal features. The significant feature extracted from the spatial domain are selected using Sequential Floating Forward Selection method and are then fed into the Support Vector Machine, Naive Bayes and Logistic Regression classifiers. Performance of the classifier is analyzed by computing the accuracy, sensitivity, specificity and positive prediction value. The performance of the classifier is also validated using the receiver operating characteristics plot. The hybrid feature from the spatial domain contributes to increase the efficiency of classification.