Future Iris Imaging with Advanced Fuzzified Histogram Equalization

Images captured under low lighting frequently exhibit low brightness, low contrast, and a small grayscale. These features can affect the individual’s view and severely limit the performance of machine vision systems, particularly when data annotation is involved. Hence, the issues motivate this study to examine the effectiveness of advanced fuzzified histogram equalization for image enhancement. A comparative study was conducted based on the low lighting condition of iris images to evaluate three image enhancement methods: Advanced Fuzzified Histogram Equalization (AFHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Fuzzy Contrast Enhancement (FCE) using the MIREIS dataset. The Gaussian membership functions (GMF) were modified accordingly to satisfy the suitable pixel intensity of the input iris images. The results were compared using the peak signal-to-noise ratio (PSNR) value, including the central processing unit (CPU) times. As a result, the AFHE showed a better PSNR value at 76.02db with faster CPU times at 4.04s compared to CLAHE and FCE. Although the PSNR value of HE is slightly lower than CLAHE (0.3%) and FCE (0.7%), AFHE improved the image’s quality and brightness, which can help other researchers with the data annotation process. The performance of the proposed methods was validated by comparing them with state-of-the-art methods. The results demonstrated that AFHE, CLAHE, and FCE exceeded other HE, AHE, CLAHE, and hybrid HE using fuzzy approaches that employed PSNR metrics.

@article{Mashudi2024,
  title     = {Future Iris Imaging with Advanced Fuzzified Histogram Equalization},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {2},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Nurul Amirah Mashudi and Norulhusna Ahmad and Rudzidatul Akmam Dziyauddin and Norliza Mohd Noor},
  doi       = {10.14569/IJACSA.2024.0150288},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150288}
}