Underwater Corrosion Recognition using Colour Illumination Mapping

Amalina Ibrahim, Wan Noorshahida Mohd Isa, Mazliham Mohd Su'ud, Shahbe Mat Desa

Abstract: Visual-based corrosion detection is one of the techniques that can be utilised for performing inspection in areas where human access is impossible because of environment, safety and other concerns such as underwater. Image quality has become a great factor in underwater image analysis. Noticeable challenges are limited source of natural lighting, loss of colour underwater at depth, magnification of objects underwater and much more. These factors may affect the process of estimating the actual corroded area underwater. Due to that, this work is proposing a technique to recognize underwater corrosion based on colour illumination mapping.