Fuzzy histogram equalization of hazy images: a concept using a type-2-guided type-1 fuzzy membership function

Nabeeha Abbasi, Mohammad Farhan Khan, Ekram Khan, Afra Alruzaiqi, Rami Al-Hmouz*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Hazy conditions, which are one of the most deleterious atmospheric scenarios, deteriorate the accuracy of autonomous vision systems during underwater, ground, and aerial operations. To improve the accuracy of these vision systems, various dehazing algorithms have been adopted in the literature. Histogram equalization is one of the most widely used low-cost image enhancement algorithms. It can be used to suppress the hazy effects in images by transforming the intensity levels of the images to new levels. However, a conventional histogram equalization method tends to degrade the natural appearance of the processed images by introducing artifacts. To overcome the limitations of histogram equalization and handle complex histogram fluctuations, a type-2-guided fuzzy logic rule is suggested in this paper. In the proposed method, the footprint of uncertainty in the fuzzy membership function is circumscribed by considering the wider region across the skeleton membership function. The purpose of adopting the footprint of uncertainty in the membership function is to handle the wide variation of hazy effects in the input images. The simulation results show that the proposed method can be used to suppress the hazy effect in input images and enhance the scene details more efficiently than contemporary histogram equalization methods for a wide range of hazy test images.

Original languageEnglish
Pages (from-to)731-745
Number of pages15
JournalGranular Computing
Issue number4
Publication statusPublished - Oct 19 2022


  • Contrast enhancement
  • Footprint of uncertainty
  • Fuzzy membership function
  • Hazy images
  • Histogram equalization

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Artificial Intelligence

Cite this