Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Novel Retinal Image Contrast Enhancement -- Fuzzy-Based Method

Adnan Shaout, Jiho Han

TL;DR

The paper tackles the challenge of poor contrast in retinal images that impedes vascular segmentation. It introduces a hybrid contrast-enhancement pipeline that linearly blends Fuzzy Contrast Enhancement (FCE) with CLAHE, followed by optional hue-based post-processing to yield more perceptually distinct retinal vessels. Evaluated on the DRIVE dataset across three versions, the approach shows that FCE+CLAHE outperforms single-method baselines, with a human survey yielding an $88\%$ preference for the proposed methods. The results demonstrate that combining fuzzy logic with histogram-based enhancement can improve preprocessing for retinal vessel segmentation in clinical workflows.

Abstract

The vascular structure in retinal images plays a crucial role in ophthalmic diagnostics, and its accuracies are directly influenced by the quality of the retinal image. Contrast enhancement is one of the crucial steps in any segmentation algorithm - the more so since the retinal images are related to medical diagnosis. Contrast enhancement is a vital step that not only intensifies the darkness of the blood vessels but also prevents minor capillaries from being disregarded during the process. This paper proposes a novel model that utilizes the linear blending of Fuzzy Contrast Enhancement (FCE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the retinal image for retinal vascular structure segmentation. The scheme is tested using the Digital Retinal Images for Vessel Extraction (DRIVE) dataset. The assertion was then evaluated through performance comparison among other methodologies which are Gray-scaling, Histogram Equalization (HE), FCE, and CLAHE. It was evident in this paper that the combination of FCE and CLAHE methods showed major improvement. Both FCE and CLAHE methods dominating with 88% as better enhancement methods proved that preprocessing through fuzzy logic is effective.

A Novel Retinal Image Contrast Enhancement -- Fuzzy-Based Method

TL;DR

The paper tackles the challenge of poor contrast in retinal images that impedes vascular segmentation. It introduces a hybrid contrast-enhancement pipeline that linearly blends Fuzzy Contrast Enhancement (FCE) with CLAHE, followed by optional hue-based post-processing to yield more perceptually distinct retinal vessels. Evaluated on the DRIVE dataset across three versions, the approach shows that FCE+CLAHE outperforms single-method baselines, with a human survey yielding an preference for the proposed methods. The results demonstrate that combining fuzzy logic with histogram-based enhancement can improve preprocessing for retinal vessel segmentation in clinical workflows.

Abstract

The vascular structure in retinal images plays a crucial role in ophthalmic diagnostics, and its accuracies are directly influenced by the quality of the retinal image. Contrast enhancement is one of the crucial steps in any segmentation algorithm - the more so since the retinal images are related to medical diagnosis. Contrast enhancement is a vital step that not only intensifies the darkness of the blood vessels but also prevents minor capillaries from being disregarded during the process. This paper proposes a novel model that utilizes the linear blending of Fuzzy Contrast Enhancement (FCE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the retinal image for retinal vascular structure segmentation. The scheme is tested using the Digital Retinal Images for Vessel Extraction (DRIVE) dataset. The assertion was then evaluated through performance comparison among other methodologies which are Gray-scaling, Histogram Equalization (HE), FCE, and CLAHE. It was evident in this paper that the combination of FCE and CLAHE methods showed major improvement. Both FCE and CLAHE methods dominating with 88% as better enhancement methods proved that preprocessing through fuzzy logic is effective.

Paper Structure

This paper contains 16 sections, 3 equations, 13 figures.

Table of Contents

  1. Introduction
  2. Proposed Model and its Methodology
  3. Fuzzy Contrast Enhancement (Version 1)
  4. Import RGB Image and G-channel Extraction
  5. Conversion to Hue-Luminosity-Saturation (HLS) format and L-Channel Extraction
  6. Fuzzy Transform of Luminosity in L Channel Image
  7. Normalization by Min-max scaling of new Luminosity
  8. Output and Its Limitations
  9. Post-processing
  10. Linear blending (Version 2)
  11. Hue adjustment for yellow output image (Version 3)
  12. Implementation
  13. Version 1 (FCE)
  14. Version 2 (FCE + CLAHE)
  15. Version 3 (FCE + CLAHE with Hue Post-processing)
  16. ...and 1 more sections

Figures (13)

  • Figure 1: Block diagram of the proposed model.
  • Figure 2: Comparison of the R, G, and B channels of the same fundus image.
  • Figure 3: Visualization of the membership functions in different mean luminosity conditions.
  • Figure 4: Comparison of the original image and FCE image, where the visibility of the vascular structure improved overall but deteriorated in the macular area.
  • Figure 5: Implementation of rules for membership functions.
  • ...and 8 more figures