An adaptive neural-fuzzy inference system (ANFIS) for detection of bruises on Chinese bayberry (Myrica rubra) based on fractal dimension and RGB intensity color

Abstract This paper introduces an adaptive neural-fuzzy inference system (ANFIS) model to detect bruises on Chinese bayberries as a function of fractal dimension (FD) and RGB intensity values. The ANFIS with different types of input membership functions (MFs) was developed. Our results showed that ‘gauss2mf’ MF performs much better than other mentioned MFs for defect inspection. The classification accuracy of the ANFIS with ‘gauss2mf’ MF was 100% and 78.57% for healthy and bruised fruits, respectively, and the total correct classification rate was 90.00%. Therefore, this study indicated the possibility of developing a potentially useful classification tool using the ANFIS technique based on FD and RGB values for detecting bruises of not only Chinese bayberries, but also of other fruits during processing, storage and distribution.