Use of Fuzzy System in the Eye Images?

In this Article, fuzzy neighbors rules are exploited to detect blood vessels in eye image. Images used in this article are chosen from eye image bank of DRIVE database including 20 retinal images. A fuzzy system consists of four segments: Fuzzy rule base, fuzzy inference engine, fuzzifier and defuzzifier. In fact, to interpret fuzzy rules set inputs need to be fuzzified which means that input variables should take a value between 0 and 1. We know that most of the images are in RGB format. Results from other researchers show that using G channel leads to better results, thus we use the same channel. Obtained results demonstrate that proposed algorithm has suitable performance. The average of accuracy parameter of 20 images is derived 92.8 %.