In this paper, we propose a radial basis function neural network (RBFNN) approach to the identification of holes in conducting plates, in the context of an eddy currents testing (ECT) signal-processing system. The system aims to localize holes in the specimen under inspection by using a two-stage approach, namely, a RBFNN followed by a least squares post-processing block. The RBFNN stage estimates the distances between the hole and the sensor probes; the least square stage identifies the hole based on the distances computed by the previous neural block. The efficacy of the proposed approach is tested on artificial data and compared with different approaches based on feedforward multilayer perceptron (MLP) and on radial basis function neural network. The robustness of the system to the introduction of white gaussian noise on the simulated data is also successfully tested.