Binary operation based hard exudate detection and fuzzy based classification in diabetic retinal fundus images for real time diagnosis applications

Abstract

Diabetic retinopathy (DR) is one of the most considerable reasons for visual impairment. The main objective of this paper is to automatically detect and recognize DR lesions like hard exudates, as it helps in diagnosing and screening of the disease. Here, binary operation based image processing for detecting lesions and fuzzy logic based extraction of hard exudates on diabetic retinal images are discused. In the initial stage, the binary operations are used to identify the exudates. Similarly, the RGB channel space of the DR image is used to create fuzzy sets and membership functions for extracting the exudates. The membership directives obtained from the fuzzy rule set are used to detect the grade of exudates. In order to evaluate the proposed approach, experiment tests are carriedout on various set of images and the results are verified. From the experiment results, the sensitivity obtained is 98.10%, specificity is 96.96% and accuracy is 98.2%. These results suggest that the proposed method could be a diagnostic aid for ophthalmologists in the screening for DR.

A review on supervised learning methodologies for detection of exudates in diabetic retinopathy

“…Exudates can be greatly recognized by its shape, size, color, texture, intensity and edge strength [8], [38], [55], [44]. Detection of all lesions [46], [58] and multiple DR stages [47], [54] is the matter of concern.…”

“…This feature set was utilized to grade patches between normal, exudate or drusen. A fuzzy logic-based categorization of hard exudates was put forward in which values of hard exudates in RGB color space were used to form the fuzzy set [57], [58]. In another attempt to classify between exudates, gaussian mixture model (GMM) was used.…”

Automated Detection of Retinal Hemorrhage based on Supervised Classifiers

“…When compared with the work of [29] the method has proved a sensitivity of 0.96 using ANN classifier against the sensitivity of 0.82 with kNN classification used in [29]. Compared with the work presented in [30], where fuzzy logic is used for classification, this method has proven superior results with a sensitivity of 0.96 against 0.86.…”

Retinal lesions classification for diabetic retinopathy using custom ResNet-based classifier

“…Transforms are applied for the preprocessing steps such as resizing, normalization, and data augmentation if needed. Figure 2 shows the results of applying the various preprocessing approaches discussed in the review papers [30]- [33] for improving the noise and resolution of fundus pictures. When employed correctly, these methods improved key performance indicators for classification models in the aforementioned assessments of the research literature.…”