In order to grade of shiitake mushroom, grading system of a shiitake mushroom with the practical corresponding algorithm was developed based on machine vision. According to length of stem, shape sorting of shiitake mushroom, and method of area, identification algorithm based on curve reconstruction was presented. With shiitake mushroom as a case study, the boundary is tracked and the curvature is calculated by tracking the boundary, and then the concave-convex quality of boundary can be distinguished with the curvature, then the possible shiitake mushroom region is found and the actual position of the shiitake mushroom can be found with the class radius of curve. Linear interpolation of edge curve of the shiitake mushroom handle removed region is performed under polar coordinate, and the shape of pileus is reconstructed, then nine shape parameters and one parameter of size are distracted based on the curve reconstructed. The shape parameters are reduced to 3 with principal component analysis. The minimum distance classifier can be constructed as the sorting model with the 3 main shape parameters as input. Considering with the identification of stem of shiitake mushroom, the final identification of the shiitake is determined on both of the shape and the size classification. Experiments shows that the accuracy of stem identification is 91.4%, and the accuracy of shape sorting can be greatly improved by identification of stem of shiitake mushroom; the precision ratio of shiitake mushroom shape grading is 95.6%,while the accuracy of shiitake mushroom grading can reach to 92.2%.