A novel contrast enhancement and denoising method for borescope images

The visual inspection based on an endoscope played an important role in diagnosis of aero-engine. However, due to the low contrast and noises, it is hard to obtain the object accurately. This paper presents a novel algorithm for image enhancement and denoising based on anisotropic diffusion and fuzzy logic theory. The maximum fuzzy entropy principle is used to map the normalized image to the fuzzy domain. Then, the image is filtered by the fractional anisotropic diffusion process iteratively. The experimental results demonstrate that the proposed method has the advantage of maximizing noise reduction and contrast enhancement, and the edges and fine details of borescope images are well preserved.