Edge detection using fuzzy inference rules and first order derivation

The edge detection in digital images based on fuzzy inference system has become popular in recent years. Several reasons can be mentioned for that, from ambiguous definition of edges to inherent uncertainty of digital images. So, this paper proposes a novel method based on fuzzy inference rules and first order derivation for edge detection in digital images. The fuzzy system of proposed approach consists of six inputs and eleven rules. This method is able to detect edges with low difference in gray level. Furthermore, the proposed method is robust at detection of edges which are created by depth discontinuity, surface orientation discontinuity, reflectance discontinuity, and illumination discontinuity. No threshold value has been determined and membership functions of the fuzzy interface system are equable for all images. According to visual view and assessment metrics we show that detected edges by proposed method are more accurate and narrow in comparison with some of common and standard methods.