Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Fuzzy Image Processing

Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing

“…The use of fuzzy image processing techniques plays an important role in producing better image quality and improved performance analysis. We investigated the capability of a combination of different fuzzy image processing techniques for the detection of diabetic retinopathy and maculopathy in eye fundus images in [8]. The proposed system implements a combination of fuzzy techniques in the image preprocessing part, which combine fuzzy filtering, followed by the fuzzy histogram equalisation and fuzzy edge detection.…”

“…3.2. The proposed system builds on the systems proposed in [7] and [8]. The previous system in [7] implements the use of fuzzy techniques for the image processing stage, including the fuzzy histogram equalisation, fuzzy median filter and fuzzy edge detection, for the purpose of one of the important lesion detection in diabetic retinopathy screening—microaneurysms.…”

“…However, the fuzzy techniques are implemented individually in different variants of the system. On the other hand, the system in [8] proposed the implementation of the combination of several fuzzy image preprocessing techniques for the detection of the maculopathy without the retinal structures localisation. Three features, which are the area of on pixels, the mean and the standard deviation of the white pixels area, are extracted from the output image for the classification stage, which classifies into two main categories with the aid of several machine learning classifiers.…”

“…Fuzzy techniques can help not only to produce better representation of images and improve the performance analysis but also can help produce a more reliable screening system. Fuzzy image processing has been reported to work well as fuzzy histogram equalisation method by Sheet et al [4], Garud et al [5] and Rahim et al [6–8]. Fuzzy filtering is another fuzzy image processing method, proposed by Patil and Chaudhari [9], Toh et al [10, 11], Kwan [12, 13] and also Rahim et al [7, 8].…”

“…Fuzzy image processing has been reported to work well as fuzzy histogram equalisation method by Sheet et al [4], Garud et al [5] and Rahim et al [6–8]. Fuzzy filtering is another fuzzy image processing method, proposed by Patil and Chaudhari [9], Toh et al [10, 11], Kwan [12, 13] and also Rahim et al [7, 8]. In addition, fuzzy edge detection can be used as a preprocessing technique in order to enhance the image quality and is reported in [7, 8].…”