Fixed point filter design for image enhancement using fuzzy logic
Farzam Farbiz, Mohammad Bagher Menhaj, Seyed Ahmad Motamedi · 2002
This paper presents a new fuzzy-logic-control based filter with the properties of removing impulsive noise and smoothing out Gaussian noise while, simultaneously, preserving edges and image details efficiently. To reach the above three goals of the image enhancement problem, we employ the concepts of fuzzy logic control to design a filter to perform all the three tasks mentioned above. This filter is mainly based on the idea that each pixel is not allowed to be uniformly fired by each of the fuzzy rules. To demonstrate how good our filtering approach works, several different cases of image enhancement problem have been considered. From the experimental results we may list the concluding remark of the proposed filtering approach: (i) no need of floating point calculations, (ii) very fast performance of the filter compared with other proposed filters, (iii) introducing a measure to demonstrate quantitatively the quality behaviour of the filters in edge preserving, (iv) high quality of filtering especially for complex images.