In this study, a natural crack model and an inversion scheme based on neural network are proposed. Their greatest advantage is that it is possible to deal with cracks whose internal conductivity is distributed and non-vanished. Therefore, it is expected to deal properly with not only electrodischarge machined (EDM) cracks but also natural cracks. Detailed explanation of the method is mentioned in this paper. After validation of the method using simulation data, it is applied to JSAEM round test problems.